video-workbench/VIDEO_WORKBENCH.md

VIDEO_WORKBENCH.md

1. Workspace Identity

This project is the local execution workspace for dimensional video, Remotion, and slide-style output.

It turns accepted GPT planning Markdown and user-provided sources into project notes, local execution plans, visual-system assets, slide/page execution folders, Remotion source projects, generated assets, renderable video files, and compact handoff material. It is optimized for practical continuation and production throughput, not heavy governance.

2. Collaboration Roles

GPT / ChatGPT   = stage 0-5 planning Markdown, outlines, visual systems, page/shot skeletons, Remotion planning briefs
User            = decisions, accepted inputs, source/reference material
Codex           = stage 6+ execution planning, Prompt Advisor work, Remotion implementation, visual-system materialization, iteration, local assets

GPT does not provide final image prompts, Codex JSON, output paths, task lists, dependency commands, render commands, complete Remotion source code, or image generation parameters. Codex should not request those from GPT as missing inputs.

For Remotion videos, accepted planning from 强哥的策划导演3.0 may provide Remotion adaptation judgment, a Remotion style-system anchor, storyboard-to-component mapping, and a Remotion Implementation Brief. The brief is a planning source, not a Codex execution package.

Codex should not rewrite GPT planning into duplicate project content. The accepted planning files belong in the project intake/ directory, and Codex turns them into local execution decisions in execution-plan.md.

3. Project Layout

All video or slide-style work lives under projects/:

projects/
  project-id/
    project.md
    intake/
    execution-plan.md
    visual-system/
      visual-system.md
      refs/
      iterations/
    remotion/
      package.json
      src/
      public/
    slides/
      slides.md
      s01/
      s02/
    tasks/

Use root-level handoff/ for repository-level, cross-project, series-level, or context-window handoff notes.

Use docs/cases/ for Codex-side local case patterns extracted from old real GPT cases. These documents preserve reusable structure, granularity, asset layering, speaker-note style, and review dimensions. They do not restore old GPT final prompts, Codex JSON execution packages, output paths, or global text-rendering rules.

Do not split projects into active, completed, abandoned, series, or standalone folders. Status and series membership belong in project files because both can change during real production.

If a series needs more structure, create projects/_series/ when the first real series needs it.

4. Project Notes

projects/<project>/project.md is a lightweight Codex-maintained note. It should record:

• project status;
• lifecycle phase from docs/workflows/project-lifecycle.md;
• workflow phase: new projects default to test/audit; switch to production-light only after explicit user authorization;
• medium type;
• worker profile, such as video-slide-production, remotion-video-production, or a future profile;
• source and reference links;
• which intake/ files are GPT planning Markdown, source notes, reference notes, or background notes;
• Remotion source root when applicable, defaulting to projects/<project>/remotion/;
• current execution focus;
• key local execution files;
• next action.

It should not duplicate the full outline, storyboard, page design, shot design, or execution plan.

5. Execution Plan

Visual projects must have:

projects/<project>/execution-plan.md

Global lifecycle rules live in:

docs/workflows/project-lifecycle.md

This is a living Codex-maintained execution control file. It records:

• the current medium branch;
• the current lifecycle phase when it affects execution;
• the active worker profile;
• the current execution focus;
• which visual-system assets need materialization;
• for Remotion projects, source root, package manager state, composition IDs, render target, render output path, and validation commands;
• the current small-batch iteration strategy;
• which sNN units are in the active batch;
• the current round;
• the next decision.

It should not repeat the project ID, full intake file index, or project map from project.md.

6. Intake

projects/<project>/intake/ holds material provided or accepted by the user:

• GPT stage 0-5 planning Markdown;
• outlines;
• storyboards, page skeletons, or shot skeletons;
• Remotion adaptation judgments, Remotion style-system anchors, Remotion storyboards, storyboard-to-component mappings, and Remotion Implementation Briefs;
• background notes;
• reference images, audio notes, or source pointers.

File naming can be agreed during the first real project. Do not create a rigid naming scheme before the real GPT outputs are known.

Intake Heading Repair

When copied GPT / LLM intake Markdown has broken heading hierarchy, use the installed fix-title Skill as an external repair capability, but keep the calling protocol local to Video Workbench.

Local calling rules:

• Repair work must run through a real Agent / subagent invocation when the runtime provides one.
• The main session should pass the source file paths, mode=artifact or mode=discussion, the fix-title skill path, and the output directory to the worker.
• The main session should not build semantic heading plans or apply heading edits itself when an Agent carrier is available.
• For files under projects/<project>/intake/, output must go under:

projects/<project>/intake-repair/fix-title-YYYY-MM-DD-<short-slug>/

The repair output package should contain:

<stem>.heading-map.json
<stem>.heading-plan.json
<stem>.fixed.md
<stem>.heading-report.md
fix-title-batch-report.md

If repaired files replace originals, first copy the original Markdown files to:

projects/<project>/intake-repair/fix-title-YYYY-MM-DD-<short-slug>/originals-before-replacement/

Main-session responsibilities after the worker returns:

• verify the returned files exist;
• inspect the heading map, plan, fixed copy, per-file report, and batch report;
• check that intended artifact files have one clear document title unless the report flags an intentional appended artifact;
• check that ambiguous appended artifacts are reported instead of silently merged;
• decide whether to replace originals, and write replacement notes when replacement happens.

Do not put durable intake repair output under tmp/. Keep reusable automation changes in skills-vault; Video Workbench owns only the local invocation protocol, project evidence, replacement notes, and supplier-request records.

7. Visual System

Visual projects use:

projects/<project>/visual-system/
  visual-system.md
  refs/
  iterations/

visual-system.md is the single record for the project's public visual system. It should cover:

• the current accepted visual system;
• materialization targets;
• trial prompts and generated reference assets;
• review notes;
• failure attribution;
• next action.

Use optional subfolders only when the project needs them:

visual-system/characters/
visual-system/scenes/
visual-system/templates/
visual-system/diagrams/
visual-system/backgrounds/
visual-system/remotion/

Do not create a separate makeup-still/ directory. Character anchors and identity references belong under visual-system/.

For Remotion projects, record the accepted Remotion style-system anchor under visual-system/remotion/ or in visual-system/visual-system.md if the project is small. It should cover background systems, color and type hierarchy, component style, information density, animation language, transition motifs, chart/flow/formula handling, subtitle strategy, and reusable component suggestions. This is source authority for the Remotion implementation; it is not React/TypeScript code.

After a character anchor stage is accepted, clean the character workspace before scene generation:

• keep only current usable character references under visual-system/characters/;
• record the active references and their intended use in visual-system/characters/character-reference-registry.md;
• move historical candidates, rejected versions, prompt/review process files, previews, masks, chroma sources, and other intermediate files to archive/characters/;
• do not use files under archive/characters/ as default prompt references unless a repair task explicitly reopens them.

For identity-critical shots, prompt specs must choose the person reference from the active character registry. Text description can clarify the role, but it does not replace the active character image reference.

8. Slides And Shots

Use slides/ as the execution unit area for video shots, PPT-style pages, Remotion scenes, and Remotion sections.

projects/<project>/slides/slides.md is the unit execution fact table. It records each page, shot, Remotion scene, or Remotion section's source, batch, current prompt/spec version, current image/render/component status, review state, acceptance state, and notes. Project-level iteration strategy belongs in execution-plan.md.

Each slides/sNN/ folder keeps one slide, page, shot, Remotion scene, or Remotion section together:

slides/
  slides.md
  s01/
    s01-metadata.json
    s01-unit-spec.md
    s01-v1-design.md      # optional; required for cover/PPT/science-video/title/post-production pages
    s01-v1-design-en.md   # optional English companion; default design remains Chinese
    s01-visual-brief.md
    s01-v1-prompt.md
    s01-v1-image.png
    s01-v1-remotion-spec.md
    s01-v1-render-check.md
    s01-v1-review.md      # optional; test/audit or explicit review only
    s01-v2-prompt.md
    s01-v2-image.png
    s01-v2-review.md      # optional; test/audit or explicit review only

All files inside sNN/ must carry the sNN prefix. Iteration files use sNN-vN-type.ext, so files from the same version sort together.

design is a human-facing design specification, not an image-generation execution card. Use sNN-vN-design.md for cover pages, PPT pages, science-video pages, title cards, explainers, Remotion scenes with meaningful typography/layout choices, and any slide that needs later human layout, typography, text placement, or post-production. It records the design concept, intended text, placement, typography/color guidance, constraints, references, and post-production notes. brief stays compact and execution-facing for Codex / image generation or Remotion implementation.

sNN-vN-design.md is Chinese by default. If an English design companion is needed, write sNN-vN-design-en.md beside it. The English companion is optional and never replaces the Chinese default.

For design-gated slides, write design first and wait for user confirmation before writing brief, prompt, Remotion specs, or generating/rendering outputs, unless the user explicitly authorizes the whole chain. Ordinary MV shot production may skip design and continue directly with brief -> prompt -> image.

For Remotion work, slides/sNN/ holds scene/section intent and checks. React/TypeScript source code lives under projects/<project>/remotion/. Do not store normal component source as append-only sNN-vN-* Markdown; use Git history for code changes and use slides/sNN/ for the scene spec, component mapping, and render evidence.

New task execution must append a new slide version instead of overwriting an existing one. Resolve the next unused vN from existing sNN-v*-* files in the slide folder, and treat incomplete or superseded earlier versions as historical evidence rather than paths to reuse.

Slide Task Orchestration

For long or context-heavy production, use local slide task orchestration:

docs/workflows/slide-task-orchestration.md
docs/workflows/slide-task-templates.md

Project-local task records go under:

projects/<project>/tasks/<task-id>/

Task records are for orchestration only. Durable slide artifacts remain under slides/sNN/.

For production work that may span multiple child sessions, keep a compact continuation file:

projects/<project>/tasks/<task-id>/production-run-status.md

This file records the target scope, completed units, active child session, next cursor, latest callback, and stop conditions. It is the default recovery surface after parent-session compression. It is not a review report and should not duplicate prompts or image evidence.

Roles:

• Main session: receives user instructions, defines worker profile / running mode / slide scope, starts child sessions, records the parent callback target, and reads handoffs after callback.
• Child session: reads shared context and handles the assigned package. In production-light, it directly writes briefs, prompts/specs, generated images or Remotion code/render outputs, slides/slides.md updates, and a compact handoff before callback.
• Slide agent: optional worker for test/audit, explicit review, repair, exception handling, or intentionally isolated slide work. It handles exactly one slide when used.

Operating lines:

• test/audit: early project setup, core-shot proving, mechanism debugging, or failure investigation. Richer handoffs, ledgers, local review files, Agent workers, and parent inspection are allowed.
• production-light: normal production after core shots or the core Remotion route have reached the expected look and the user authorizes the switch in project.md. Keep the content line (brief, prompt/spec, generated image or Remotion source/render, slides/slides.md) and compact recovery handoff; omit routine review, Agent workers, packet/return files, and audit records.

Defaults:

• Worker profile for current video / MV work: video-slide-production.
• Worker profile for Remotion videos: remotion-video-production.
• Design-gated slides: cover, PPT, science-video, title, explainer, and post-production-heavy pages require sNN-vN-design.md before brief.
• Child session capacity: at most 8 ordinary production slides; reduce to 1-3 for identity-heavy, repair-heavy, core-risk, or context-expensive scopes.
• Production-light topology: main session -> child session directly.
• Test/audit topology: main session -> child session -> optional slide Agent.
• Slide agent capacity when used: exactly 1 slide.
• Execution is sequential by default; do not run child sessions or slide agents in parallel unless the user explicitly changes the rule.
• Parent orchestration is callback-only by default: after dispatch, the main session stops routine waiting; the child session wakes the parent with status, topology, resolved versions, handoff path, and image paths if complete.
• Callback is the child session's final action: all allowed project writes, slides/slides.md updates, narrow required checks, and the compact handoff must be complete before callback; after a successful callback the child must not write or verify additional project files.
• Polling is a fallback only when callback tooling is unavailable or the user explicitly requests polling for a named run.
• Production-light review mode: none.
• Future ppt-page-production work is reserved and may use docs/cases/, but it must not inherit video-slide rules blindly.

The user controls task running mode:

• prompt only: create briefs and prompts; do not generate images.
• prompt and generate: create briefs and prompts, then generate images for the task's recorded slide scope.
• remotion plan only: create Remotion execution specs and mappings; do not write source code.
• remotion implement: write or edit Remotion source and run narrow source checks; do not render final MP4 unless the task also authorizes rendering.
• remotion render: write or edit source as needed, run narrow source checks, and render the target MP4.

Task-level generation or Remotion render instructions count as user approval for the named scope and mode. In production-light, generated images are recorded as production-pass outputs without per-image user review or routine final verification; the user can request an append-only retry later if a result is not usable. Remotion source/render work is code work and must run the task's narrow checks before closeout. Core, repair, identity-heavy, otherwise high-risk slides, or uncertain Remotion animation systems may still pause if the task plan says they require sampling or explicit review.

For unattended production, the parent session repeats the callback loop from docs/workflows/project-lifecycle.md: update production-run-status.md, dispatch one child session, wait for callback, reload the minimal project/task state, then dispatch the next package if no stop condition is present. Exact parent context/token usage is not required for continuation because Codex may auto-compress the parent session; file-backed state is the authority.

Visual-system rules:

• visual-system/ is the production authority.
• Style continuity must use visual-system/style/style-prompt-master.md.
• Character continuity must use visual-system/characters/character-reference-registry.md and active character reference images.
• Visible character identity cannot be generated from text-only prompts when identity matters.
• Slide prompts must use the gpt-image-2 Skill Advisor / host-native workflow.
• Remotion implementation must use the installed Remotion Skill before code edits. Read C:\Users\wangq\.agents\skills\remotion\SKILL.md, then read relevant rules/*.md files for the task area.

Remotion project rules:

• Default source root: projects/<project>/remotion/.
• Default deliverable: source code plus renderable MP4.
• One-off project-specific Remotion source belongs in Video Workbench. Reusable products, reusable templates, deployable systems, and business software belong in work-projects unless the user explicitly keeps a prototype local.
• The user has standing task-level permission for Remotion tasks to use npx create-video, npm dependency installation, and Remotion render commands when needed. Normal sandbox/network approval requests still apply at command time.
• Keep source code, package files, and source assets in Git by default. Keep node_modules, caches, build outputs, and rendered media ignored by default.
• Use projects/<project>/remotion/public/ for assets referenced with Remotion staticFile() unless a task records a different local convention.
• Use projects/<project>/renders/ or projects/<project>/exports/ for MP4 outputs unless the task records another render path.
• For Remotion code, normal source edits are not append-only sNN-vN-* artifacts; use Git history and code review. Append-only rules still apply to Markdown control artifacts, scene specs, render checks, and generated media receipts.

Review rules:

• Production-light review defaults to none.
• Test/audit review defaults to local-only unless the task says otherwise.
• Do not call Minimax MCP or other external vision/review services unless the user explicitly authorizes that task.
• Generated production slides can be tracked in tasks/<task-id>/task-log.md and slides/slides.md instead of a full per-slide review.
• Remotion render checks are source/render validation, not external visual review. Record the command, composition ID, output path, and result in the compact handoff or a sNN-vN-render-check.md file when the check is scene-specific.

9. Investigations

Use investigations/ for research reports, experiments, comparisons, draft workflow proposals, and other reviewable evidence.

tmp/ is deprecated and should not receive new durable work. Short-lived scratch material should either be deleted or promoted into investigations/ when it becomes useful evidence.

garden-gpt-image-2/ remains reserved for tool-level image prompt or workflow traces when that path is used.

10. Word Budget

Use the default standard:

1 minute = about 220 Chinese characters of voiceover
10 minutes = about 2200 Chinese characters

Adjust only when the user specifies a different narration speed.

11. Asset Policy

Image and audio generation can be automated when available skills or APIs are appropriate.

Video generation from images remains manual or semi-manual for now because output reliability varies. Remotion is a separate programmatic video path: use it when the accepted plan calls for React/TypeScript animation, scene composition, captions, charts, diagrams, or renderable MP4 output from source code.

Editing and publishing are human-controlled unless explicitly automated later.

Codex is the default prompt owner for final image prompts in this workspace, but final prompts must be produced through the gpt-image-2 Skill workflow rather than direct freehand drafting. GPT planning Markdown remains a source specification, not a final prompt.

For project-bound image prompts, Codex must:

• run the gpt-image-2 mode check before prompt work;
• read the relevant Skill template or reference file;
• save the rendered prompt/spec as a reviewable project file;
• list the source files actually used;
• wait for user approval before image generation.

A task-level user instruction that records prompt and generate plus the slide scope counts as generation approval for that task scope. A task recorded as prompt only never authorizes image generation.

Direct prompts may exist only as clearly labeled scratch or non-generation-ready drafts. They must be rebuilt through the gpt-image-2 Skill workflow before use.

Reference-Capable Image Generation

The current and future default success path for project-bound reference generation is:

gpt-image-2 Skill Advisor prompt/spec
→ load the real reference image into the conversation context
→ call host image_gen with the loaded image assigned an explicit role
→ copy the selected output into the project or investigation
→ record prompt, input reference path, output path, and compact handoff/status

This route was validated in:

investigations/2026-06-24-s14-reference-capable-generation/

Use this path instead of API/Garden image generation for normal Video Workbench work. Do not reopen the "can references work" question for ordinary project-bound image generation unless the host image tool is unavailable, the reference file cannot be loaded, or the user explicitly changes the policy.

For every reference-capable generation:

• the prompt must still be produced through the gpt-image-2 Skill workflow;
• the actual image reference must be loaded into the conversation context before generation;
• the prompt must name the loaded image role, such as Image 1: identity reference, Image 1: style reference, or Image 1: edit target;
• merely writing a local path in the prompt is not enough;
• the output must be copied from the host-generated default location into the project, investigation, or other durable workspace path;
• the compact handoff or task status must record whether the generation used the verified host reference-by-visible-context path; a slide-agent return receipt is required only when the task actually uses a slide Agent in test/audit, repair, exception, or explicit review mode.

Reference selection defaults:

Shot or asset need	Default reference choice
Near shot, face, half-profile, expression, identity-heavy frame	Use the matching crop reference first.
Distant shot, landscape-led frame, aerial / wide scene, low identity burden	Use the accepted character anchor board or project-approved distant reference first.
Medium action, back view, walking pose, prop continuity	Use the matching crop, transparent slice, or anchor board according to the visible direction.
High identity fidelity project with many close shots	Consider creating higher-resolution crops through image-to-image from the accepted anchor board before production.

For 在路上-style landscape-led MV projects, a crop set derived from the accepted character anchor board and made transparent is sufficient by default when the goal is consistency rather than high-fidelity portrait likeness.

12. Capability-Request Mode

When a required capability is missing, create a supplier ticket and pause the dependent work.

Tickets go to:

requirements/ccpe/
requirements/skills-vault/

Use requirements/ccpe/ for local work agents, CCPE-Lite artifacts, agent specs, runtime rules, model cards, invocation contracts, and governed cognitive assets.

Use requirements/skills-vault/ for deterministic automation tools, scripts, exporters, batch processors, and installable automation skills.

13. Text Encoding

All local project documents are UTF-8 unless a file explicitly declares another encoding.

When using PowerShell to read Markdown, JSON, YAML, text, handoff, prompt, or discussion files, use explicit UTF-8:

Get-Content -LiteralPath <path> -Encoding UTF8
Select-String -Path <path> -Pattern <pattern> -Encoding UTF8

Do not wait for mojibake or a failed first read before applying UTF-8.

14. CCPE Consumption

Video Workbench consumes CCPE through the single external interface:

C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md

When preparing CCPE integration or invocation work, read Interface.md first and follow it to:

C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccpe-agent-consumer-setup.md

Do not duplicate canonical CCPE definitions here. Do not hardcode Agent, Lite, Skill, Runtime, or protocol paths as default entrypoints. Use ccpe-consumption/ for interface notes and future project-local invocation setup records.

Reusable or canonical expert agents belong in CCPE. Project-local slide task orchestration, child-session records, and slide-agent packets belong in Video Workbench and are not formal CCPE participant output. If this workflow is later packaged as deployable software, production/business agent implementation belongs in the target software project, not in Video Workbench.