chore(version): 0.27.0 → 0.26.1 — 새 bump 규칙상 patch
진행 로그 개선은 검색·색인 결과 불변 + 새 명령/플래그/config 없음 + additive-only wire(asset_phase)라 CLAUDE.md 신규 규칙(기능/인터페이스 변경=minor, 없으면 patch)상 patch 가 맞음. version·라벨·HOTFIXES 헤더를 0.26.1 로 정정. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
48
Cargo.lock
generated
48
Cargo.lock
generated
@@ -4724,7 +4724,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-app"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"base64 0.22.1",
|
||||
@@ -4772,7 +4772,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-chunk"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4790,7 +4790,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-cli"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"clap",
|
||||
@@ -4811,7 +4811,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-config"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"dirs 5.0.1",
|
||||
@@ -4827,7 +4827,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-core"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4841,7 +4841,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-embed"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4855,7 +4855,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-embed-candle"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"candle-core",
|
||||
@@ -4875,7 +4875,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-embed-local"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"fastembed",
|
||||
@@ -4888,7 +4888,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-embed-ollama"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-config",
|
||||
@@ -4903,7 +4903,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-eval"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-app",
|
||||
@@ -4922,7 +4922,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-llm"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-core",
|
||||
@@ -4931,7 +4931,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-llm-local"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-config",
|
||||
@@ -4948,7 +4948,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-mcp"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-app",
|
||||
@@ -4966,7 +4966,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-nli"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"hf-hub",
|
||||
@@ -4981,7 +4981,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-code"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"gix",
|
||||
@@ -5004,7 +5004,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-image"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"ab_glyph",
|
||||
"anyhow",
|
||||
@@ -5028,7 +5028,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-md"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-core",
|
||||
@@ -5045,7 +5045,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-pdf"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -5060,7 +5060,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-rag"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -5082,7 +5082,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-search"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"globset",
|
||||
@@ -5101,7 +5101,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-source-fs"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -5119,7 +5119,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-store-sqlite"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -5139,7 +5139,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-store-vector"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"arrow",
|
||||
@@ -5163,7 +5163,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-tui"
|
||||
version = "0.27.0"
|
||||
version = "0.26.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"crossterm",
|
||||
|
||||
@@ -32,7 +32,7 @@ edition = "2024"
|
||||
rust-version = "1.85"
|
||||
license = "MIT OR Apache-2.0"
|
||||
repository = "https://github.com/altair823/kebab"
|
||||
version = "0.27.0" # v0.27.0 — ingest 진행 로그 개선: TTY 진행바에 현재 파일명 + 느린 phase(ocr/caption/embed)+모델명 실시간 + 경과초 heartbeat `(Ns)`, 종료 시 최장 소요 파일 top-5 요약. 신규 wire 이벤트 `asset_phase{idx,total,phase,model}` + `asset_timings.ocr_ms`/`caption_ms` 추가(additive, ingest_progress.v1 유지, serde default 0). 기본 동작 불변. — CLAUDE.md §Release
|
||||
version = "0.26.1" # v0.26.1 — ingest 진행 로그 개선: TTY 진행바에 현재 파일명 + 느린 phase(ocr/caption/embed)+모델명 실시간 + 경과초 heartbeat `(Ns)`, 종료 시 최장 소요 파일 top-5 요약. 신규 wire 이벤트 `asset_phase{idx,total,phase,model}` + `asset_timings.ocr_ms`/`caption_ms` 추가(additive, ingest_progress.v1 유지, serde default 0). 기본 동작 불변. — CLAUDE.md §Release
|
||||
|
||||
# pre-v0.18 workspace-wide cleanup: enable clippy::pedantic group with
|
||||
# intentional allow-list. The allowed lints are either cosmetic (doc style),
|
||||
|
||||
@@ -35,7 +35,7 @@ P0~P5 직렬. P6~P9 P5 이후 병렬 가능.
|
||||
|
||||
머지 후 발견된 모든 deviation / hotfix 의 dated 로그는 [tasks/HOTFIXES.md](tasks/HOTFIXES.md). 본 요약은 \"누군가가 인수받을 때 알아두면 시간을 많이 절약하는\" 항목만:
|
||||
|
||||
- **2026-06-03 ingest 진행 로그 개선** — v0.27.0. 이미지/PDF + OCR/caption on 볼트 ingest 가 "멈춘 듯" 보이던 문제 해소: TTY 진행바에 현재 파일명 + 느린 phase(ocr/caption/embed)+모델명 + 경과초 `(Ns)` heartbeat, 종료 시 최장 소요 파일 top-5 요약. 신규 wire `asset_phase{idx,total,phase,model}` + `asset_timings.ocr_ms`/`caption_ms`(additive, `ingest_progress.v1` 유지, serde default 0). 이미지·PDF 경로도 `asset_timings` emit(이전 markdown 만). 기본 동작 불변. 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03 ingest 진행 로그), spec/plan `docs/superpowers/{specs,plans}/2026-06-03-ingest-log-improve-*.md`.
|
||||
- **2026-06-03 ingest 진행 로그 개선** — v0.26.1. 이미지/PDF + OCR/caption on 볼트 ingest 가 "멈춘 듯" 보이던 문제 해소: TTY 진행바에 현재 파일명 + 느린 phase(ocr/caption/embed)+모델명 + 경과초 `(Ns)` heartbeat, 종료 시 최장 소요 파일 top-5 요약. 신규 wire `asset_phase{idx,total,phase,model}` + `asset_timings.ocr_ms`/`caption_ms`(additive, `ingest_progress.v1` 유지, serde default 0). 이미지·PDF 경로도 `asset_timings` emit(이전 markdown 만). 기본 동작 불변. 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03 ingest 진행 로그), spec/plan `docs/superpowers/{specs,plans}/2026-06-03-ingest-log-improve-*.md`.
|
||||
- **2026-06-03 arctic-embed-l-v2.0 임베더 통합** — v0.26.0. 별칭 제거 후 설명형 query recall 보강(측정 recall@10 130/132, e5 +7). `kebab-embed-candle` 모델 레지스트리화(e5 mean + `snowflake-arctic-embed-l-v2.0` CLS, 모델별 pooling/prefix) + 신규 `kebab-embed-ollama`(`provider="ollama"`, `/api/embed`). config `endpoint: Option<String>` 추가. 기본 e5 유지(opt-in), arctic 전환은 embedding_version cascade → 재색인. candle↔Ollama cosine>0.99 게이트로 pooling/prefix 정확성 고정(`#[ignore]`). 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03 arctic), spec `docs/superpowers/specs/2026-06-03-arctic-embedder-spec.md`.
|
||||
- **2026-06-03 doc-side expansion(별칭) 기능 완전 제거** — v0.25.0. 아래 2026-05-31 항목의 색인-시 청크당 LLM 별칭 생성 + 별칭 검색 채널을 **전부 제거**(ROI 음수: cross-lingual 은 e5-large 단독으로 충분, 기여는 설명형 +2 그룹뿐인데 대가가 청크당 색인-시 LLM). `Chunk.aliases`/`expansion.rs`/`IngestExpansionCfg`/alias lexical arm/`expansion_progress` wire kind 제거, 신규 마이그레이션 **V013** 이 `chunk_aliases_fts`+`chunks.aliases` DROP. 별칭 default-off 였어 사용자 체감 0, 기존 KB 도 재색인 불요(잔존 별칭 벡터는 `strip_alias_suffix` graceful 매핑/`reset` 정리). `AssetTimings.expansion_ms` 는 wire 호환 위해 값 0 으로 유지. 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03), spec `docs/superpowers/specs/2026-06-03-remove-doc-expansion-spec.md`.
|
||||
- **2026-05-31 Phase 2 doc-side expansion 별칭(개별 dense 벡터) + 파생물 캐시(V012)** — v0.21.0 cut. 색인 시 LLM 이 청크별 별칭("같은 의미 다른 표현")을 생성, 줄별 **개별 dense 벡터**(sentinel `{chunk}#alias#N`)로 색인 (묶음 1벡터는 평균화 희석으로 회귀 → 폐기) + boilerplate 청크 skip. `[ingest.expansion]` default off. 측정(나무위키 ~1000 문서 CS corpus): 변형 일관성 14/18 → **16/18**, spread 0.222→0.111, 대조군 false-positive 별칭 무죄. 비용 병목(별칭 18문서 2.5h)은 **파생물 캐시(V012, 청크 내용 해시 키)**로 해소 — 정답 3개 cold 1879s → warm 13s **≈ 145배**, embedding+별칭 LLM 캐싱, version_key cascade 정합. search/ask 가 `kebab.sqlite`+`lancedb` 만으로 동작 → 외부 서버 색인 후 DB 만 복사하는 이식 워크플로 가능. **결정/known limitation**: grounded/refusal 판정이 부분 인용을 grounded 로 오분류(정직한 거부가 false-positive 로 집계) — 별도 개선 후보. stack·svm 설명형 2개 잔존. 자세한 내용: `tasks/HOTFIXES.md` (2026-05-31), 측정: `docs/superpowers/handoffs/2026-05-31-namu-wiki-alias-cache-study.md`.
|
||||
|
||||
@@ -96,7 +96,7 @@ pub enum IngestEvent {
|
||||
/// `idx/total` while its per-chunk phases churn. `chunks` is the chunk
|
||||
/// count for asset `idx`.
|
||||
AssetChunked { idx: u32, total: u32, chunks: u32 },
|
||||
/// v0.27.0 (additive): emitted when an asset enters a *slow* internal
|
||||
/// v0.26.1 (additive): emitted when an asset enters a *slow* internal
|
||||
/// phase, so the interactive progress bar can show **which** phase
|
||||
/// (and which model) is currently running instead of looking frozen.
|
||||
/// `phase` ∈ {`"ocr"`, `"caption"`, `"embed"`}; short phases
|
||||
@@ -121,8 +121,8 @@ pub enum IngestEvent {
|
||||
/// them so the slowest-asset summary attributes vision-model time
|
||||
/// correctly. `expansion_ms` is retained for wire compatibility but is
|
||||
/// always 0 since doc-side expansion was removed (HOTFIXES 2026-06-03).
|
||||
/// `ocr_ms` / `caption_ms` (v0.27.0) are additive with serde default 0
|
||||
/// so pre-v0.27.0 consumers deserialize cleanly.
|
||||
/// `ocr_ms` / `caption_ms` (v0.26.1) are additive with serde default 0
|
||||
/// so pre-v0.26.1 consumers deserialize cleanly.
|
||||
AssetTimings {
|
||||
idx: u32,
|
||||
total: u32,
|
||||
@@ -312,7 +312,7 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn asset_timings_ocr_caption_default_to_zero_for_legacy_wire() {
|
||||
// v0.27.0 additive: a pre-v0.27.0 wire payload omits ocr_ms /
|
||||
// v0.26.1 additive: a pre-v0.26.1 wire payload omits ocr_ms /
|
||||
// caption_ms; serde `default` must fill 0 so old producers stay
|
||||
// compatible.
|
||||
let legacy = serde_json::json!({
|
||||
@@ -339,7 +339,7 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn asset_phase_serializes_with_discriminator() {
|
||||
// v0.27.0 additive variant — `kind` must be snake_case
|
||||
// v0.26.1 additive variant — `kind` must be snake_case
|
||||
// `asset_phase`, `phase` is the slow-phase label, `model` the
|
||||
// model id (nullable).
|
||||
let ev = IngestEvent::AssetPhase {
|
||||
|
||||
@@ -1350,7 +1350,7 @@ fn ingest_one_asset(
|
||||
let store_ms = u64::try_from(t_store.elapsed().as_millis()).unwrap_or(u64::MAX);
|
||||
|
||||
// Embed + vector upsert (only when both sides are configured).
|
||||
// v0.27.0: surface the embed phase + model so a long embed run reads as
|
||||
// v0.26.1: surface the embed phase + model so a long embed run reads as
|
||||
// "embedding(<model>)…" rather than a frozen bar (markdown path too).
|
||||
crate::ingest_progress::emit(
|
||||
progress,
|
||||
@@ -1578,7 +1578,7 @@ fn ingest_one_image_asset(
|
||||
let lang_hint = lang_hint_from_doc(&canonical);
|
||||
let now = time::OffsetDateTime::now_utc();
|
||||
let mut warning_notes: Vec<String> = Vec::new();
|
||||
// v0.27.0: vision phases (OCR / caption) are the usual bottleneck on an
|
||||
// v0.26.1: vision phases (OCR / caption) are the usual bottleneck on an
|
||||
// image-heavy vault and emitted no progress before — so the bar looked
|
||||
// frozen. Surface each as an `AssetPhase` and measure its wall-clock for
|
||||
// the slowest-asset summary.
|
||||
@@ -1771,7 +1771,7 @@ fn ingest_one_image_asset(
|
||||
}
|
||||
let embed_ms = u64::try_from(t_embed.elapsed().as_millis()).unwrap_or(u64::MAX);
|
||||
|
||||
// v0.27.0: per-phase timing for the image path — ocr_ms / caption_ms
|
||||
// v0.26.1: per-phase timing for the image path — ocr_ms / caption_ms
|
||||
// carry the vision-model cost so the slowest-asset summary attributes
|
||||
// an image-heavy run's bottleneck correctly.
|
||||
crate::ingest_progress::emit(
|
||||
@@ -2360,7 +2360,7 @@ fn ingest_one_pdf_asset(
|
||||
}
|
||||
let embed_ms = u64::try_from(t_embed.elapsed().as_millis()).unwrap_or(u64::MAX);
|
||||
|
||||
// v0.27.0: per-phase timing for the PDF path. `ocr_ms` reuses the
|
||||
// v0.26.1: per-phase timing for the PDF path. `ocr_ms` reuses the
|
||||
// page-OCR total already computed above so a scanned-PDF run's OCR cost
|
||||
// shows up in the slowest-asset summary; caption is markdown/image-only.
|
||||
crate::ingest_progress::emit(
|
||||
|
||||
@@ -32,7 +32,7 @@ use time::format_description::well_known::Rfc3339;
|
||||
|
||||
use crate::wire;
|
||||
|
||||
/// v0.27.0: number of slowest assets surfaced in the end-of-run summary.
|
||||
/// v0.26.1: number of slowest assets surfaced in the end-of-run summary.
|
||||
/// Constant for now (spec defers the config knob).
|
||||
const SLOWEST_TOP_N: usize = 5;
|
||||
|
||||
@@ -72,19 +72,19 @@ impl ProgressMode {
|
||||
pub struct ProgressDisplay {
|
||||
mode: ProgressMode,
|
||||
bar: Option<ProgressBar>,
|
||||
/// v0.27.0 heartbeat: start `Instant` of the asset currently in
|
||||
/// v0.26.1 heartbeat: start `Instant` of the asset currently in
|
||||
/// flight, shared with the bar's steady-tick custom template key so
|
||||
/// the `(Ns)` elapsed counter advances *between* events (the drain
|
||||
/// loop blocks on `recv()`, so without the ticker the counter would
|
||||
/// freeze). `None` while scanning / between assets / after completion.
|
||||
asset_start: Arc<Mutex<Option<Instant>>>,
|
||||
/// v0.27.0: workspace path of the asset currently in flight — set on
|
||||
/// v0.26.1: workspace path of the asset currently in flight — set on
|
||||
/// `AssetStarted`, reused by `AssetPhase` to render `{path} · {phase}…`.
|
||||
current_path: Option<String>,
|
||||
/// v0.27.0 slowest summary: idx → path, captured from `AssetStarted`
|
||||
/// v0.26.1 slowest summary: idx → path, captured from `AssetStarted`
|
||||
/// so `AssetTimings` (which only carries `idx`) can name the asset.
|
||||
asset_paths: HashMap<u32, String>,
|
||||
/// v0.27.0 slowest summary: (path, total_ms) per asset that reported
|
||||
/// v0.26.1 slowest summary: (path, total_ms) per asset that reported
|
||||
/// `AssetTimings`. Sorted + truncated to top-N on `Completed`.
|
||||
timings: Vec<(String, u64)>,
|
||||
}
|
||||
@@ -151,7 +151,7 @@ impl ProgressDisplay {
|
||||
if let Some(bar) = self.bar.as_mut() {
|
||||
bar.set_length(u64::from(*total));
|
||||
bar.set_position(0);
|
||||
// v0.27.0: a custom `{asset_elapsed}` key reads the shared
|
||||
// v0.26.1: a custom `{asset_elapsed}` key reads the shared
|
||||
// per-asset start `Instant` and appends ` (Ns)`. Combined
|
||||
// with the steady tick below, the elapsed counter advances
|
||||
// even while the drain loop is blocked on `recv()` waiting
|
||||
@@ -198,18 +198,18 @@ impl ProgressDisplay {
|
||||
path,
|
||||
media,
|
||||
} => {
|
||||
// v0.27.0: remember the path so AssetPhase can render it and
|
||||
// v0.26.1: remember the path so AssetPhase can render it and
|
||||
// the slowest summary (keyed by idx in AssetTimings) can name
|
||||
// the asset.
|
||||
self.current_path = Some(path.clone());
|
||||
self.asset_paths.insert(*idx, path.clone());
|
||||
// v0.27.0: (re)start the per-asset heartbeat clock.
|
||||
// v0.26.1: (re)start the per-asset heartbeat clock.
|
||||
if let Ok(mut guard) = self.asset_start.lock() {
|
||||
*guard = Some(Instant::now());
|
||||
}
|
||||
if let Some(bar) = self.bar.as_ref() {
|
||||
bar.set_position(u64::from(idx.saturating_sub(1)));
|
||||
// v0.27.0: show the current filename on the bar (TTY).
|
||||
// v0.26.1: show the current filename on the bar (TTY).
|
||||
// Previously position-only — the interactive user couldn't
|
||||
// tell which file was in flight. The steady tick redraws
|
||||
// in place, so this no longer pollutes scrollback.
|
||||
@@ -222,7 +222,7 @@ impl ProgressDisplay {
|
||||
}
|
||||
IngestEvent::AssetFinished { .. } => {
|
||||
// Position is advanced in AssetStarted; bar.finish_and_clear()
|
||||
// in Completed handles the final state. v0.27.0: stop the
|
||||
// in Completed handles the final state. v0.26.1: stop the
|
||||
// heartbeat clock so the bar doesn't show a stale `(Ns)` in the
|
||||
// gap before the next AssetStarted.
|
||||
if let Ok(mut guard) = self.asset_start.lock() {
|
||||
@@ -230,7 +230,7 @@ impl ProgressDisplay {
|
||||
}
|
||||
self.current_path = None;
|
||||
}
|
||||
// v0.27.0: an asset entered a slow internal phase (ocr / caption /
|
||||
// v0.26.1: an asset entered a slow internal phase (ocr / caption /
|
||||
// embed). Surface which phase + model is running so a multi-second
|
||||
// vision-model call no longer looks frozen.
|
||||
IngestEvent::AssetPhase {
|
||||
@@ -276,7 +276,7 @@ impl ProgressDisplay {
|
||||
caption_ms,
|
||||
..
|
||||
} => {
|
||||
// v0.27.0: accumulate (path, total_ms) for the slowest summary.
|
||||
// v0.26.1: accumulate (path, total_ms) for the slowest summary.
|
||||
// total = every measured phase (expansion_ms is always 0).
|
||||
let total_ms = parse_ms + chunk_ms + embed_ms + store_ms + ocr_ms + caption_ms;
|
||||
if let Some(path) = self.asset_paths.get(idx) {
|
||||
@@ -287,7 +287,7 @@ impl ProgressDisplay {
|
||||
}
|
||||
if !quiet {
|
||||
let mut err = std::io::stderr().lock();
|
||||
// v0.27.0: only print ocr / caption when they actually ran
|
||||
// v0.26.1: only print ocr / caption when they actually ran
|
||||
// (markdown leaves them 0) so the text path stays uncluttered.
|
||||
let mut parts = vec![
|
||||
format!("parse {}", fmt_ms(*parse_ms)),
|
||||
@@ -320,7 +320,7 @@ impl ProgressDisplay {
|
||||
"ingest: complete (scanned={} new={} updated={} skipped={} errors={})",
|
||||
counts.scanned, counts.new, counts.updated, counts.skipped, counts.errors,
|
||||
);
|
||||
// v0.27.0: slowest-asset summary. Useful in both TTY and
|
||||
// v0.26.1: slowest-asset summary. Useful in both TTY and
|
||||
// non-TTY (it pinpoints the bottleneck file), so it prints
|
||||
// unless --quiet. --json mode never reaches here (emit_json).
|
||||
let _ = write_slowest_summary(&mut err, &self.timings, SLOWEST_TOP_N);
|
||||
@@ -404,7 +404,7 @@ fn fmt_ms(ms: u64) -> String {
|
||||
}
|
||||
}
|
||||
|
||||
/// v0.27.0: shorten an over-long workspace path for the progress-bar
|
||||
/// v0.26.1: shorten an over-long workspace path for the progress-bar
|
||||
/// message so the live `(Ns)` heartbeat suffix stays visible on a narrow
|
||||
/// terminal. Keeps the tail (filename + a couple of parents) — that's the
|
||||
/// distinguishing part — and prefixes `…` when truncated. Paths up to the
|
||||
@@ -423,7 +423,7 @@ fn abbreviate_path(path: &str) -> String {
|
||||
format!("…{tail}")
|
||||
}
|
||||
|
||||
/// v0.27.0: render the end-of-run "slowest assets" summary. Sorts
|
||||
/// v0.26.1: render the end-of-run "slowest assets" summary. Sorts
|
||||
/// `(path, total_ms)` descending by time, takes the top `n`, and writes a
|
||||
/// compact table to `w`. No-op (writes nothing) when `timings` is empty so
|
||||
/// a run with no per-asset timing (e.g. all-skipped) prints no stray header.
|
||||
|
||||
@@ -161,7 +161,7 @@ fn apply_event(state: &mut IngestState, event: IngestEvent) {
|
||||
// no-ops here (the CLI / --json surfaces render them).
|
||||
| IngestEvent::AssetChunked { .. }
|
||||
| IngestEvent::AssetTimings { .. }
|
||||
// v0.27.0 slow-phase hint (ocr / caption / embed): the CLI bar uses
|
||||
// v0.26.1 slow-phase hint (ocr / caption / embed): the CLI bar uses
|
||||
// it for a live phase message; the TUI status-bar reducer tracks only
|
||||
// per-asset counters, so it's a no-op here.
|
||||
| IngestEvent::AssetPhase { .. } => {}
|
||||
|
||||
@@ -37,15 +37,15 @@
|
||||
"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 (v0.27.0): the slow internal phase the asset just entered. Short phases (parse/chunk/store) are not emitted." },
|
||||
"model": { "type": ["string", "null"], "description": "asset_phase (v0.27.0): model performing the phase — vision LLM id for ocr/caption, embedder model_id for embed. null when the phase runs without a configured model." },
|
||||
"phase": { "type": "string", "enum": ["ocr", "caption", "embed"], "description": "asset_phase (v0.26.1): the slow internal phase the asset just entered. Short phases (parse/chunk/store) are not emitted." },
|
||||
"model": { "type": ["string", "null"], "description": "asset_phase (v0.26.1): 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 (v0.27.0, 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 (v0.27.0, additive, default 0): image caption phase wall-clock (ms). 0 on markdown / PDF paths." },
|
||||
"ocr_ms": { "type": "integer", "minimum": 0, "description": "asset_timings (v0.26.1, 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 (v0.26.1, 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." },
|
||||
|
||||
@@ -14,7 +14,7 @@ historical contract that was implemented; this file accumulates the
|
||||
deltas so phase 5+ readers can find the live behavior without diffing
|
||||
git history.
|
||||
|
||||
## 2026-06-03 — ingest 진행 로그 개선: 파일명·phase·heartbeat·slowest 요약 (v0.27.0)
|
||||
## 2026-06-03 — ingest 진행 로그 개선: 파일명·phase·heartbeat·slowest 요약 (v0.26.1)
|
||||
|
||||
**무엇을 왜 추가했나.** arctic 도그푸딩 중 이미지/PDF 혼재 + OCR/caption on 볼트에서
|
||||
ingest 가 중간부터 느려졌는데, TTY 진행바가 **파일명·현재 phase·모델·경과시간**을 안 보여
|
||||
|
||||
Reference in New Issue
Block a user