tasteforge-video

affaan-m ｜ 設計與前端 ｜ 原文 ｜ MIT

離線規劃品味訪談、風格包驗證、套用與可編輯時間軸匯出

---
name: tasteforge-video
description: 用在檔案驅動的多模態圖像、影片和 3D 素材探索；taste 訪談；distill 或 apply 工作流；風格包驗證；可編輯的 EDL/FCPXML 匯出；來源溯源稽核；以及必須在 provider 生成之前就 fail closed 的離線規劃。
metadata:
  origin: ECC
---

# TasteForge Video

要完整獨立的創意 pipeline，先用 `taste-distillation`，再用
`taste-application`。這兩個 ECC skill 直接附帶它們的 Python script：
量測參考片、生成或直通既有的 take、調色、剪輯、
合成、驗證，再交接給 Blender 和 Resolve。這個流程不需要另外的影片
repo。這個 skill 記錄的是 ECC 打包好的離線引擎，以及它嚴格的證據規範。

TasteForge 把「讓它感覺像這個參考」變成可重複、
可檢查的 workflow：訪談品味、把它提煉成結構化的風格
包、驗證風格包、把它量測到的節奏和外觀套用到本機媒體，
再匯出可編輯的時間軸。標準實作是
放在 ECC 裡 `skills/taste-application/scripts/tasteforge/` 的
`tasteforge` 套件。`Ito-Markets/ito-video` 是一個
使用這個打包 ECC 引擎的範例專案。

## 何時使用

- 使用者要求在拍任何素材之前**先訪談影片品味**
  （「問我關於外觀的事」、「訪談我的美學方向」）。
- 使用者想要把**美學提煉成結構化的約束**，也就是可重複使用的
  風格包，而不是感覺（「把這些參考變成一個包」）。
- 使用者想要**驗證風格包**（metadata 完整嗎、符合 schema 嗎、
  節奏量測了嗎、規格提煉了嗎？）。
- 使用者想要**把風格包套用到本機素材**：依風格包量測到的
  節奏，在本機片段上以確定性的方式規劃剪輯。
- 使用者想要**匯出 EDL/FCPXML**：給 DaVinci Resolve / Premiere / Final Cut 的
  可編輯、逐格精準的交接。
- 使用者要求**生成媒體的溯源稽核**：這個風格包、規格或剪輯是從哪來的；
  哪些是本機量測的、哪些是 provider 生成的；
  哪些是 dry-run。
- 使用者要求**從本機參考檔案探索或規劃檔案驅動的多模態圖像、影片或
  3D 素材輸出**，包括分開的 manifest、
  以主體為錨點的 CV 效果，或 Resolve 效果配方。
- 使用者提到 TasteForge、風格包、flashethereal、taste distillation、
  節奏規劃、多模態探索、distill/apply 工作流，或是
  影片的 taste 訪談。

## 本機確定性操作 vs. Provider 生成

這條界線是這個相容性 skill 的核心。它的操作都是
**本機、確定性、離線**：

| 操作 | 確定性？ | ECC 可以執行 |
|---|---|---|
| Taste 訪談 → profile | 是（離線） | 可以 |
| 風格包檢視 / 依 schema 驗證 | 是 | 可以 |
| 提煉 profile（+ 量測依據）→ 規格 | 是（dry-run 語意） | 可以 |
| 把風格包節奏套到本機媒體 → 報告 + 時間軸 | 是 | 可以 |
| 匯出 EDL (CMX3600) / FCPXML 1.9 | 是 | 可以 |
| 溯源 / 譜系報告 | 是 | 可以 |
| 用視覺模型提煉靜態圖 | **provider 生成** | **不可以** |
| Reference-to-video、image-to-3D、託管 compose | **provider 生成** | **不可以** |

**Provider 生成在 ECC 裡必須 fail closed。** 任何實際的 Fal（或其他
provider）呼叫，包括生成鏡頭、產出道具 mesh、託管的 VLM
提煉，都需要在另一條獨立的 lane 下，明確另外授權執行，並有它自己的 review。在這條相容性 lane 裡，ECC 絕不呼叫 Fal、絕不讀任何 API
key 或其他憑證（包括 `FAL_KEY`）、不上傳任何媒體，也不更動
任何 provider 帳號的狀態。當請求需要 provider 生成時，要明確
說出這條界線，跑完本機那一半（訪談、風格包驗證、
規劃、匯出），然後停手。

**絕不宣稱 Fal workflow 已經存好。** 本機對 Fal endpoint、
model id 或 dry-run URL 的引用（它們會出現在風格包 metadata 裡）都是
**僅供參考**：它絕不代表 provider 那邊有 workflow 被存好、
持久化，或被授權執行。離線產出的任何東西都帶有
dry-run/dry_run 語意，要說「dry-run 規格」或「確定性計畫」，絕不說
「由模型生成」。

## 標準實作

- Repository：`affaan-m/ECC`；Python 發行包 `ecc-tasteforge`，套件
  目錄 `skills/taste-application/scripts/tasteforge/`。從
  解壓縮的 ECC 套件安裝：`python3 -m pip install ./skills/taste-application/scripts`。
  範例專案 `Ito-Markets/ito-video` 釘在特定的 ECC commit。
- CLI：`python3 -m tasteforge <command>`，有 `provenance`、`inspect`、`validate`、
  `interview`、`distill`、`apply`、`export`、`multimodal`。`--live` flag 會以
  exit code 2 結束並拒絕。
- Schema 就是契約：taste profile、風格包 manifest、grade、cadence、
  規格、時間軸事件、套用報告（`provider` 以 enum 鎖定為
  `"none"`；`dry_run` 鎖定為 `true`）。
- 還原來源的譜系和刻意排除的項目，放在 repo 的
  `skills/taste-application/SOURCE.md`。執行 `python3 -m tasteforge provenance` 可取得機器
  可讀的版本。

本機確定性指令要用已安裝的 ECC 引擎，並解讀
它輸出的 JSON。沒有的話就安裝打包好的引擎；不要在
行內重寫它的邏輯。`taste.resolve` 是 `tasteforge.resolve` 的相容性 import，
所以創意 script 和範例專案共用同一個驗證過的 Resolve adapter。

`python3 -m tasteforge` CLI 使用已安裝的 `ecc-tasteforge` 發行包。獨立的 `taste-distillation` 和 `taste-application`
script 則放在 ECC 選擇性加入的媒體生成模組裡，有它們自己的 Python
需求。兩條路徑都不需要公開使用者的 repo 或媒體。

要繼續使用已存的 checkout 之前，先記錄它的 commit，並檢查本機 branch
和 worktree 有沒有後續的實作修正。跑標準套件的測試，
和 `python3 -m tasteforge apply --help`；ECC 的文字和 fixture 測試
不能證明被選到的 Python checkout 有實作這份契約。

## 串接創意 Skill

| 階段 | 負責者 | 可審查的成果 |
|---|---|---|
| 創意方向 | `taste` | 命名風格、參考觀察、選定的外觀和避免清單 |
| 提煉與規劃 | `tasteforge-video` | 量測證據、分開的風格規格、dry-run manifest 和節奏計畫 |
| 剪輯與特效 | `video-editing`，搭配選定的渲染器，例如 Remotion、Manim 或 Fusion | 套用後的素材、實際的軌道、可編輯的特效和時間軸 |
| 選用的生成素材或配音 | `fal-ai-media` 或選定的音訊 workflow，在它自己的授權下 | Provider receipt 和檢查過的輸出 |
| 交付 | 剪輯 workflow，需要時再用 `content-engine` | 審查過的確切匯出和發布文案 |

只用專案需要的階段。`taste` skill 歷史上的
angelcore/cloud-trance 色盤和拍點語法只是選用的創意範例；
它們不能覆蓋目前的 brief，也不能把不同編號的風格混在一起。
各風格的方向要用它自己實際的參考，包括 3D Cyber Glitch
和 Fluid Sketch。TasteForge 不取代這些 skill，也不要求每一種
渲染器。3D 的材質、幾何、線框行為、
運動和構圖，都要明確寫在該風格的特徵裡。3D 請求 manifest
是素材的計畫，它不是 mesh。主體錨點描述子只是指名一個
追蹤需求，它不是主體已被偵測或追蹤到的證據。
在宣稱 CV 特效已可靠套用之前，要先檢查實際的軌道、追蹤丟失時的行為，
和 render 出來的主體畫格。

## 工作流

1. **訪談**（`interview`）：收集外觀各軸的答案：色盤、
   顆粒、打光、焦距、攝影機運動、主體構圖、調色、
   情緒形容詞、避免清單，另外單獨收集內容 brief。外觀
   和內容要分開；合在一起是經典的失敗。
2. **提煉**（`distill`）：離線把 profile 對應到規格 schema，
   有提供風格包時，把風格包量測到的依據（黑/白點、對比、
   各分區色度、色盤、剪輯節奏）嵌進去。結果
   是 dry-run 規格：確定性、provider 為 `"none"`。
3. **驗證**（`validate` / `inspect`）：依 schema 檢查風格包；
   回報錯誤與警告（只有 metadata 的風格包缺少靜態圖，
   是警告，不是錯誤）。
4. **套用**（`apply`）：依風格包量測到的節奏規劃鏡頭長度
   （有 seed、確定性），套在使用者的本機片段上；產出
   套用報告和逐格精準的時間軸事件。
5. **匯出**（`export`）：寫出 CMX3600 EDL + FCPXML 1.9，用有理數、
   NTSC 安全的時間，好匯入真正的 NLE。
6. **稽核**（`provenance`）：回報譜系：還原來源的 digest、
   生成歷史、fixture 來源、provider 引用只當作
   指標記錄。

### 套用真實素材而不重複來源

當 brief 要求不重複片段時，要用支援
`apply --no-repeat --fps` 的標準 checkout，並明確設定輸出影格率。如果沒有這些
flag，就回報實作上的缺口，不要悄悄改用
舊版的 round-robin 選擇。嚴格模式讓每個正規化後的來源路徑
最多只用一次，依 manifest 順序，並拒絕不足或太短的來源。
要準備足夠多、審查過的 select 來填滿節奏計畫。這是來源層級的
唯一性，不代表支援同一段錄影裡不同的 in/out 範圍。

套用報告只是剪輯計畫。它不做視覺上的鏡頭排名、
不幫素材調色、不套 LUT、不 render 疊加，也不匯入 Resolve 專案。
風格包量測到的參考節奏，要跟輸出影格率分開。

export CLI 要的是 `{"clips": [...]}`。匯出之前，要把套用結果的
`timeline_events` 包到 `clips` 底下，並傳入套用時用的同一個 `--fps`；
export 預設的影格率不能把計畫重新 conform。
把時間軸交給剪輯 workflow 之前，要檢查輸出的事件數、總影格數、不重複的來源，
和媒體連結。
當那個 workflow 在 NLE 裡套用重疊的特效時，要配置相容的
軌道，並讀回每一個要求的起點、終點和長度。只有
回傳的項目或 append 呼叫成功，並不能證明每個排定的特效
都被放上去了；在 render 之前，要拒絕遺失、偏移或被截斷的 placement。

## 檔案驅動的多模態契約

當本機參考必須驅動圖像、影片和 3D 素材輸出的 dry-run 生成計畫，
同時又要保持風格分離時，用這條路徑：

```bash
python3 -m tasteforge multimodal --config workflow.json --out-dir out/multimodal
```

config 會列出編號的風格和本機證據檔案。這些候選
風格要保持分開，不要混成一個通用的美學：

1. Flash Ethereal
2. 3D Cyber Glitch
3. Fluid Sketch

這個指令用 ffprobe/ffmpeg 量測本機參考，每個風格輸出一份風格
規格、分開的圖像、影片和 3D 素材 manifest、溯源，以及
一份 Resolve 特效配方。特效排程必須是有 seed 的非週期。CV
特效需要真正的主體錨點，它的丟失追蹤政策必須剛好是
`disable_effect_until_track_recovers`；`continue_without_anchor` 和其他所有
政策都 fail closed。每個特效都帶有 placement 約束，
要保護臉部和可讀的文字，並防止裝飾性的角落 mesh 取代全畫面的 3D 作品。

回傳的 receipt 就是 bundle 的邊界。它用相對路徑、位元組大小、SHA-256、風格、模態、
`provider_execution:false` 和精確的參考/時間溯源，綁住每一個輸出的證據
產物。receipt 要求 `provider_calls:0` 必須是精確的整數（JSON 布林值 `false` 無效），
`provider_execution:false`，以及 `dry_run:true`。每份風格規格也
要求明確的 `dry_run:true`。Resolve 特效配方要求同樣的
精確整數 `provider_calls:0`、`provider_execution:false` 和 `dry_run:true`。
每個模態 manifest 和每個巢狀請求，都必須包含全部四個精確的
fail-closed 欄位：整數 `provider_calls:0`、`provider_execution:false`、
`dry_run:true` 和 `submit:false`；每個請求另外還要求
`provider_call_mode:"disabled"`。缺少欄位就是拒絕，不是預設值，
而 `dry_run:false` 必須在寫出任何輸出之前就被拒絕。

在時間軸、證據、probe 和來源長度資料裡，布林值一律當成無效數字。
每個這類數值都必須是有限的實數：拒絕
`true`、`false`、NaN、無限大、負的事件起點、非正的長度、
超出範圍的證據時間，以及結束時間超過所宣告的有限
正時間軸的事件。整檔證據使用明確的整檔時間基準，
絕不捏造時間戳。

receipt 的參考是長度的權威來源。每個驗證過的參考長度都以它引用的 SHA-256 當 key；
同一個 digest 的重複出現，長度必須一致，否則 bundle 無效。
每個特效證據的 `source_duration` 和每個主體錨點的 `source_duration`，
都必須等於那個 digest 驗證過的 receipt 長度，不能只是
包含它引用的時間。Probe 長度和所有 probe 量測，必須描述
用來算位元組數和 SHA-256 的同一份穩定位元組。如果來源在 probe 時被更動，
或在它仍然可用時重新雜湊得到不同結果，就 fail closed，
不要輸出或接受 receipt。

建立之後一定要跑 bundle 驗證。缺少圖像、影片或 3D 素材
manifest 必須 fail closed。被通用化或重複的風格、週期性排程、
沒有錨點的 CV 特效、缺少 placement 約束、provider 執行 flag、
沒有綁定的輸出檔、位元組大小漂移，或 SHA-256 被竄改，都必須 fail closed。
要拒絕是 symlink 的輸出根目錄、中間產物或產物，也要拒絕
特殊檔案（包括 FIFO 和裝置）；輸出必須是
真實目錄樹底下的一般檔案。如果本機的 `ffmpeg` 或 `ffprobe` 不可用，
CLI 必須回傳它有界的、非零的本機媒體處理錯誤，而且不能有 Python
traceback。不要靠刪除證據或削弱驗證來修復失敗的 receipt。

## 範例流程

```bash
# after installing the ECC engine; paths below are your project inputs
python3 -m tasteforge validate stylepacks/flashethereal
python3 -m tasteforge interview --answers answers.json --genre flashethereal --out profile.json
python3 -m tasteforge distill --profile profile.json --pack stylepacks/flashethereal --out spec.json
python3 -m tasteforge apply --pack stylepacks/flashethereal --media media.json --duration 20 --out report.json
python3 -m tasteforge export --events events.json --out-dir out --title flashethereal-cut
python3 -m tasteforge provenance
```

當鏡頭必須生成時，要在使用者明確的 provider 授權下，把審查過的 brief
和風格方向交給 `taste-application`。離線 CLI 仍然維持
fail-closed；它的計畫和可編輯時間軸，不能證明有任何
provider 工作跑過。

---
name: tasteforge-video
description: Use for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workflows; style-pack validation; editable EDL/FCPXML export; provenance audits; and offline planning that must fail closed before provider generation.
metadata:
  origin: ECC
---

# TasteForge Video

For the complete standalone creative pipeline, use `taste-distillation` then
`taste-application`. Those ECC skills ship their Python scripts directly:
measure references, generate or pass through existing takes, grade, cut,
composite, verify, and hand off to Blender and Resolve. No separate video
repository is required for that flow. This skill documents ECC's packaged offline engine and its strict evidence contract.

TasteForge turns "make it feel like this reference" into a repeatable,
inspectable workflow: interview taste, distill it into a structured style
pack, validate the pack, apply its measured cadence and look to local media,
and export an editable timeline. The canonical implementation is the
`tasteforge` package shipped inside ECC at
`skills/taste-application/scripts/tasteforge/`. `Ito-Markets/ito-video` is an
example project that consumes the packaged ECC engine.

## When to Use

- The user asks to **interview for video taste** before any footage is made
  ("ask me about the look", "interview me about aesthetic direction").
- The user wants to **distill an aesthetic into structured constraints** — a
  reusable style pack rather than vibes ("turn these references into a pack").
- The user wants to **validate a style pack** (is the metadata complete,
  schema-valid, cadence measured, spec distilled?).
- The user wants to **apply a style pack to local footage** — plan a cut from
  the pack's measured cadence over local clips, deterministically.
- The user wants to **export EDL/FCPXML** — an editable, frame-exact handoff
  to DaVinci Resolve / Premiere / Final Cut.
- The user asks for a **generated-media provenance audit** — where did this
  pack, spec, or cut come from; what was measured locally versus generated by
  a provider; what was dry-run.
- The user asks to **discover or plan file-driven multimodal image, video, or
  3D-asset outputs** from local reference files, including separate manifests,
  subject-anchored CV effects, or Resolve effect recipes.
- The user mentions TasteForge, style packs, flashethereal, taste distillation,
  cadence/rhythm planning, multimodal discovery, distill/apply workflows, or a
  taste interview for video.

## Local Deterministic Operations vs Provider Generation

This boundary is the core of this compatibility skill. Its operations are
**local, deterministic, and offline**:

| Operation | Deterministic? | ECC may run |
|---|---|---|
| Taste interview → profile | yes (offline) | yes |
| Pack inspect / validate against schemas | yes | yes |
| Distill profile (+ measured grounding) → spec | yes (dry-run semantics) | yes |
| Apply pack cadence to local media → report + timeline | yes | yes |
| Export EDL (CMX3600) / FCPXML 1.9 | yes | yes |
| Provenance / lineage report | yes | yes |
| Vision-model distillation of stills | **provider generation** | **no** |
| Reference-to-video, image-to-3D, hosted compose | **provider generation** | **no** |

**Provider generation must fail closed in ECC.** Any live Fal (or other
provider) call — generating shots, minting prop meshes, hosted VLM
distillation — requires explicit separately authorized execution under a
separate lane with its own review. In this compatibility lane, ECC never calls Fal, never reads any API
key or other credentials (`FAL_KEY` included), uploads no media, and mutates
no provider account state. When a request needs provider generation, state
exactly that boundary, run the local half (interview, pack validation,
planning, export), and stop.

**Never claim a Fal workflow is saved.** A local reference to a Fal endpoint,
model id, or dry-run URL (they appear inside pack metadata) is
**reference-only**: it never means a provider-side workflow was saved,
persisted, or is authorized to run. Anything produced offline carries
dry-run/dry_run semantics — say "dry-run spec" or "deterministic plan", never
"generated by the model".

## Canonical Implementation

- Repository: `affaan-m/ECC`; Python distribution `ecc-tasteforge`, package
  directory `skills/taste-application/scripts/tasteforge/`. Install from the
  extracted ECC package with `python3 -m pip install ./skills/taste-application/scripts`.
  The example project `Ito-Markets/ito-video` pins a specific ECC commit.
- CLI: `python3 -m tasteforge <command>` — `provenance`, `inspect`, `validate`,
  `interview`, `distill`, `apply`, `export`, `multimodal`. `--live` flags exit
  with code 2 and refuse.
- Schemas are the contract: taste profile, pack manifest, grade, cadence,
  spec, timeline events, application reports (`provider` is enum-locked to
  `"none"`; `dry_run` to `true`).
- Recovered-source lineage and deliberate exclusions live in the repo's
  `skills/taste-application/SOURCE.md`. Run `python3 -m tasteforge provenance` for the machine-
  readable version.

Use the installed ECC engine for local deterministic commands and interpret
its JSON. Install the packaged engine if absent; do not reconstruct its logic
inline. `taste.resolve` is a compatibility import of `tasteforge.resolve`, so
the creative scripts and example project share one verified Resolve adapter.

The `python3 -m tasteforge` CLI uses the installed `ecc-tasteforge` distribution. The standalone `taste-distillation` and `taste-application`
scripts ship in ECC's opt-in media-generation module with their own Python
requirements. Neither path requires publishing the user's repository or media.

Before resuming a saved checkout, record its commit and inspect local branches
and worktrees for later implementation fixes. Run the canonical package's tests
and `python3 -m tasteforge apply --help`; ECC's text and fixture tests do not
prove that the selected Python checkout implements this contract.

## Chaining the Creative Skills

| Stage | Owner | Reviewable result |
|---|---|---|
| Creative direction | `taste` | Named genres, reference observations, chosen look and avoid list |
| Distillation and planning | `tasteforge-video` | Measured evidence, separate genre specs, dry-run manifests and cadence plan |
| Editing and effects | `video-editing`, with the chosen renderer such as Remotion, Manim, or Fusion | Applied footage, actual tracks, editable effects and timeline |
| Optional generated assets or voice | `fal-ai-media` or the selected audio workflow, under its own authorization | Provider receipt and inspected output |
| Delivery | Editing workflow, then `content-engine` when requested | Reviewed exact export and distribution copy |

Use only the stages the project needs. The `taste` skill's historical
angelcore/cloud-trance palette and beat grammar are optional creative examples;
they must not override the current brief or merge distinct numbered genres.
Use each genre's actual references for its direction, including 3D Cyber Glitch
and Fluid Sketch. TasteForge does not replace these skills or require every
renderer. Keep 3D materials, geometry, wireframe behavior,
motion, and composition explicit in the genre signature. A 3D request manifest
is a plan for an asset; it is not a mesh. A subject-anchor descriptor names a
tracking requirement; it is not evidence that a subject was detected or tracked.
Inspect actual tracks, track-loss behavior, and rendered subject frames before
claiming that CV effects have been applied reliably.

## Workflow

1. **Interview** (`interview`): collect answers for the look axes — palette,
   grain, lighting, focal length, camera motion, subject framing, grade,
   mood adjectives, avoid list — and separately the content brief. Keep look
   and content separate; merging them is the classic failure.
2. **Distill** (`distill`): map the profile onto the spec schema offline,
   embedding the pack's measured grounding (black/white point, contrast,
   per-zone chroma, palette, cut rhythm) when a pack is supplied. The result
   is a dry-run spec: deterministic, provider `"none"`.
3. **Validate** (`validate` / `inspect`): check the pack against its schemas;
   report errors vs warnings (missing stills in a metadata-only pack are a
   warning, not an error).
4. **Apply** (`apply`): plan shot durations from the pack's measured cadence
   (seeded, deterministic) over the user's local clips; produce the
   application report and frame-exact timeline events.
5. **Export** (`export`): write CMX3600 EDL + FCPXML 1.9 with rational,
   NTSC-safe times for import into a real NLE.
6. **Audit** (`provenance`): report lineage — recovered-source digests,
   generation history, fixture provenance, provider references as
   pointer-only records.

### Applying Real Footage Without Repeated Sources

When the brief requires no repeated clips, use a canonical checkout supporting
`apply --no-repeat --fps`, and set the output frame rate explicitly. If those
flags are absent, report the implementation gap rather than silently using
legacy round-robin selection. Strict mode uses each normalized source path at
most once in manifest order and rejects insufficient or too-short sources.
Prepare enough reviewed selects to fill the cadence plan. This is source-level
uniqueness, not support for distinct in/out ranges from the same recording.

The application report is a cut plan. It does not perform visual shot ranking,
grade footage, apply a LUT, render overlays, or import a Resolve project.
Keep the pack's measured reference cadence separate from the output frame rate.

The export CLI expects `{"clips": [...]}`. Wrap the application's
`timeline_events` under `clips` before exporting, and pass the same `--fps`
used for application; export's default frame rate must not reconform the plan.
Check the emitted event count, total frames, unique sources, and media linkage
before handing the timeline to the editing workflow.
When that workflow applies overlapping effects in an NLE, allocate compatible
tracks and read back every requested start, end, and duration. A returned item
or a successful append call alone does not prove that every scheduled effect
was placed; reject missing, shifted, or truncated placements before rendering.

## File-Driven Multimodal Contract

Use this path when local references must drive dry-run generation plans for
image, video, and 3D-asset outputs while preserving genre separation:

```bash
python3 -m tasteforge multimodal --config workflow.json --out-dir out/multimodal
```

The config names numbered genres and local evidence files. Keep these candidate
genres distinct rather than blending them into one generic aesthetic:

1. Flash Ethereal
2. 3D Cyber Glitch
3. Fluid Sketch

The command measures local references with ffprobe/ffmpeg and emits one style
spec per genre, separate image, video, and 3D-asset manifests, provenance, and
a Resolve effect recipe. The effect schedule must be seeded aperiodic. CV
effects require a real subject anchor whose exact lost-track policy is
`disable_effect_until_track_recovers`; `continue_without_anchor` and every
other policy fail closed. Every effect carries placement constraints that
preserve faces and readable type and prevent decorative corner meshes from
replacing full-frame 3D work.

The returned receipt is the bundle boundary. It binds every emitted evidence
artifact by relative path, byte size, SHA-256, genre, modality,
`provider_execution:false`, and exact reference/time provenance. The receipt
requires `provider_calls:0` as an exact integer (the JSON boolean `false` is
invalid), `provider_execution:false`, and `dry_run:true`. Every genre spec also
requires explicit `dry_run:true`. The Resolve effect recipe requires that same
exact integer `provider_calls:0`, `provider_execution:false`, and `dry_run:true`.
Every modality manifest and every nested request must contain all four exact
fail-closed fields: integer `provider_calls:0`, `provider_execution:false`,
`dry_run:true`, and `submit:false`; each request also requires
`provider_call_mode:"disabled"`. A missing field is a rejection, not a default,
and `dry_run:false` must be rejected before output is written.

Treat booleans as invalid numbers everywhere in timeline, evidence, probe, and
source-duration data. Every such numeric value must be a finite real: reject
`true`, `false`, NaN, infinities, negative event starts, non-positive durations,
out-of-range evidence times, and events ending beyond the declared finite
positive timeline. Whole-file evidence uses an explicit whole-file time basis
and never invents timestamps.

Receipt references are the duration authority. Key each validated reference
duration by its cited SHA-256; duplicate occurrences of one digest must agree
on duration or the bundle is invalid. Every effect evidence `source_duration`
and every subject-anchor `source_duration` must equal that digest's validated
receipt duration, not merely contain its cited time. Probe duration and all
probe measurements must describe the same stable bytes used for byte count and
SHA-256. If the source mutates while probing or rehashes differently while it
is still available, fail closed rather than emitting or accepting a receipt.

Always run bundle validation after creation. A missing image, video, or 3D-asset
manifest must fail closed. Genericized or duplicate genres, periodic schedules,
unanchored CV effects, missing placement constraints, provider-execution flags,
unbound output files, byte-size drift, or SHA-256 tampering must fail closed.
Reject output roots, intermediates, or artifacts that are symlinks, and reject
special files (including FIFOs and devices); outputs must remain regular files
under a real directory tree. If local `ffmpeg` or `ffprobe` is unavailable, the
CLI must return its bounded nonzero local-media-processing error without a
Python traceback. Do not repair a failed receipt by deleting evidence or
weakening validation.

## Example Session

```bash
# after installing the ECC engine; paths below are your project inputs
python3 -m tasteforge validate stylepacks/flashethereal
python3 -m tasteforge interview --answers answers.json --genre flashethereal --out profile.json
python3 -m tasteforge distill --profile profile.json --pack stylepacks/flashethereal --out spec.json
python3 -m tasteforge apply --pack stylepacks/flashethereal --media media.json --duration 20 --out report.json
python3 -m tasteforge export --events events.json --out-dir out --title flashethereal-cut
python3 -m tasteforge provenance
```

When shots must be generated, pass the reviewed brief and style direction to
`taste-application` under the user's explicit provider authorization. The
offline CLI remains fail-closed; its plans and editable timelines do not prove
a provider job ran.