altair823
aeaa18a564
OCR/caption 켜진 볼트 ingest 가 중간부터 느릴 때 TTY 진행바가 파일명·phase·
모델·경과시간을 안 보여 "멈춤"처럼 보이던 문제 해결.
- 신규 wire AssetPhase{idx,total,phase,model} + AssetTimings.ocr_ms/caption_ms
(additive, ingest_progress.v1 유지)
- app: apply_ocr/apply_caption/embed 진입 시 AssetPhase emit + ocr/caption 시간 측정
- cli: TTY 진행바에 현재 파일명 + phase(model) + asset 경과초(heartbeat),
종료 시 최장 소요 파일 top-5 요약(quiet 여도 출력, --json 미출력)
- wire schema / README / HANDOFF / HOTFIXES 동기화, version 0.26.0 → 0.27.0
검증(리더): clippy 0, kebab-app/cli 61그룹·parse-image/tui 14그룹 0실패(-j8).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
74 lines
6.2 KiB
JSON
74 lines
6.2 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://kb.local/wire/v1/ingest_progress.schema.json",
|
|
"title": "IngestProgressEvent v1",
|
|
"description": "Streaming progress event emitted by `kebab ingest --json`. One event per line (line-delimited JSON). Discriminated by `kind`. The terminal events are `completed` and `aborted` — every ingest run ends with exactly one of them. The final stdout line of a `--json` ingest is still the existing `ingest_report.v1` for backwards compatibility; progress events stream above it.",
|
|
"type": "object",
|
|
"required": ["schema_version", "kind", "ts"],
|
|
"properties": {
|
|
"schema_version": { "const": "ingest_progress.v1" },
|
|
"kind": {
|
|
"type": "string",
|
|
"enum": [
|
|
"scan_started",
|
|
"scan_completed",
|
|
"asset_started",
|
|
"asset_finished",
|
|
"asset_chunked",
|
|
"asset_phase",
|
|
"asset_timings",
|
|
"embed_batch_started",
|
|
"embed_batch_finished",
|
|
"pdf_ocr_started",
|
|
"pdf_ocr_finished",
|
|
"completed",
|
|
"aborted"
|
|
]
|
|
},
|
|
"ts": { "type": "string", "format": "date-time", "description": "RFC 3339 timestamp at the moment the event was emitted." },
|
|
"root": { "type": "string", "description": "scan_started: workspace root being walked." },
|
|
"total": { "type": "integer", "minimum": 0, "description": "scan_completed / asset_started / asset_finished: total assets discovered." },
|
|
"idx": { "type": "integer", "minimum": 1, "description": "asset_started / asset_finished: 1-based index of the current asset within the scan." },
|
|
"path": { "type": "string", "description": "asset_started: workspace-relative path of the asset being processed." },
|
|
"media": { "type": "string", "description": "asset_started: media kind label (e.g. `markdown`, `pdf`, `image`)." },
|
|
"result": {
|
|
"type": "string",
|
|
"enum": ["new", "updated", "skipped", "error"],
|
|
"description": "asset_finished: per-asset outcome (mirrors `ingest_report.v1.items[].kind`)."
|
|
},
|
|
"chunks": { "type": "integer", "minimum": 0, "description": "asset_finished / asset_chunked (v0.24.0): chunk count produced for this asset." },
|
|
"phase": { "type": "string", "enum": ["ocr", "caption", "embed"], "description": "asset_phase (v0.26.0): the slow internal phase the asset just entered. Short phases (parse/chunk/store) are not emitted." },
|
|
"model": { "type": ["string", "null"], "description": "asset_phase (v0.26.0): model performing the phase — vision LLM id for ocr/caption, embedder model_id for embed. null when the phase runs without a configured model." },
|
|
"parse_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.24.0, additive): parse phase wall-clock (ms). Emitted by markdown / image / PDF paths." },
|
|
"chunk_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.24.0, additive): chunk phase wall-clock (ms). Emitted by markdown / image / PDF paths." },
|
|
"expansion_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.24.0, additive): retained for wire compatibility but always 0 — doc-side expansion was removed (HOTFIXES 2026-06-03)." },
|
|
"embed_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.24.0, additive): embed + vector phase wall-clock (ms) — embedding, vector upsert, and stale-vector purge." },
|
|
"store_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.24.0, additive): SQLite persist phase wall-clock (ms) — put_asset/document/blocks/chunks only." },
|
|
"ocr_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.26.0, additive, default 0): image/PDF OCR phase wall-clock (ms). 0 on the markdown path (no OCR)." },
|
|
"caption_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.26.0, additive, default 0): image caption phase wall-clock (ms). 0 on markdown / PDF paths." },
|
|
"n_chunks": { "type": "integer", "minimum": 0, "description": "embed_batch_started / embed_batch_finished: chunks in this embedding batch." },
|
|
"ms": { "type": "integer", "minimum": 0, "description": "embed_batch_finished / pdf_ocr_finished: wall-clock duration (ms). pdf_ocr_finished skip path 의 의미는 mixed (DCTDecode 부재 시 0, engine 실패 시 latency-before-bail)." },
|
|
"chars": { "type": "integer", "minimum": 0, "description": "pdf_ocr_finished: char count of OCR result. Skip 시 0." },
|
|
"page": { "type": "integer", "minimum": 1, "description": "pdf_ocr_started / pdf_ocr_finished: 1-based PDF page number under OCR." },
|
|
"ocr_engine": { "type": "string", "description": "pdf_ocr_finished: engine_name (e.g. 'ollama-vision')." },
|
|
"skipped": { "type": "boolean", "description": "pdf_ocr_finished: true 일 시 OCR 미수행 (DCTDecode 부재 또는 engine 실패). chars=0 만으로는 skip 과 0-char result 구분 불가." },
|
|
"image_byte_size": { "type": "integer", "minimum": 0, "description": "pdf_ocr_finished (optional, v0.20.x): raster image byte size." },
|
|
"image_width": { "type": "integer", "minimum": 0, "description": "pdf_ocr_finished (optional, v0.20.x): raster image width px." },
|
|
"image_height": { "type": "integer", "minimum": 0, "description": "pdf_ocr_finished (optional, v0.20.x): raster image height px." },
|
|
"failure_reason": { "type": "string", "description": "pdf_ocr_finished (optional, v0.20.x): OCR failure reason. Present iff skipped=true due to engine error. Values: timeout | ocr_error | network_error | other." },
|
|
"counts": {
|
|
"type": "object",
|
|
"description": "completed / aborted: aggregate counters at the moment the run ended (mirrors fields on `ingest_report.v1`).",
|
|
"properties": {
|
|
"scanned": { "type": "integer", "minimum": 0 },
|
|
"new": { "type": "integer", "minimum": 0 },
|
|
"updated": { "type": "integer", "minimum": 0 },
|
|
"skipped": { "type": "integer", "minimum": 0 },
|
|
"errors": { "type": "integer", "minimum": 0 },
|
|
"chunks_indexed": { "type": "integer", "minimum": 0 },
|
|
"embeddings_indexed": { "type": "integer", "minimum": 0 }
|
|
}
|
|
}
|
|
}
|
|
}
|