# Release 分階段交付

## 階段劃分

### Phase 1：Sentence Chunk Embedding 交付

**觸發時機**: ASR + ASRX 完成 + Rule 1 Ingestion 完成

**交付內容**:
- `{uuid}.asr.json`
- `{uuid}.asrx.json`
- chunks（chunk_type = 'sentence'）
- chunk_vectors（sentence embedding）
- DB schema + chunks table data

**用途**: 終端使用者可進行語意搜尋

### Phase 2：5W1H Summary Chunk Embedding 交付

**觸發時機**: 全部 processor 完成 + Rule 3 Ingestion + 5W1H Agent

**交付內容**:
- Phase 1 全部內容
- `{uuid}.cut.json`
- `{uuid}.yolo.json`
- `{uuid}.face.json`
- `{uuid}.pose.json`
- `{uuid}.ocr.json`
- chunks（chunk_type = 'cut', 'visual', 'trace', 'story'）
- chunk_vectors（summary embedding）
- identities / identity_bindings / face_detections

**用途**: 完整搜尋 + 摘要 + 人物識別

---

## Worker Pipeline 整合

```
ASR  完成 → ASRX 完成
       ↓
   Rule 1 Ingestion (sentence chunks)
       ↓
   Phase 1 Release Packaging ← 自動
       ↓
   其餘 Processors 繼續
       ↓
   Rule 3 Ingestion (cut chunks + 5W1H summary)
       ↓
   Phase 2 Release Packaging ← 自動
```

## 產出目錄結構

```
release/
├── phase1/
│   ├── v1.0.0_20260509_120000/
│   │   ├── output_json/      ← asr.json, asrx.json
│   │   ├── schema.sql        ← chunks table DDL
│   │   ├── chunks.csv        ← sentence chunks data
│   │   ├── vectors.csv       ← sentence embeddings
│   │   └── RELEASE_INFO.txt
│   └── latest → v1.0.0_20260509_120000
│
└── phase2/
    ├── v1.0.0_20260509_140000/
    │   ├── output_json/      ← all processor outputs
    │   ├── schema.sql        ← full schema
    │   ├── chunks.csv        ← all chunks
    │   ├── vectors.csv       ← all embeddings
    │   ├── identities.csv    ← person identities
    │   └── RELEASE_INFO.txt
    └── latest → v1.0.0_20260509_140000
```