altair823
cd2213e48d
- 신규 모듈 `crates/kebab-parse-image/src/caption.rs` 추가:
• `caption_image(llm, bytes, lang_hint, cfg)` — `&dyn LanguageModel`
위에서 동작. 비전 LM (예: gemma4:e4b) 이 한 문장 객관 설명
출력. temperature=0 / seed=0 결정성.
• `apply_caption(llm, bytes, block, lang_hint, cfg, events)` —
`block.caption = Some(...)` 으로 채우고 ProvenanceKind::CaptionApplied
이벤트 1건 추가. `image.caption.enabled = false` 면 클린 no-op
(Ok(())). LM 실패 시 block.caption None 그대로 + events 미기록.
• 다운스케일 long-edge `[128, 1536]` 클램프. PNG passthrough hot
path 보존, 그 외는 단일 디코드 + PNG 재인코딩.
• 한국어 / 영어 프롬프트 분기 (lang_hint=\"ko\"/\"kor\" → 한국어).
• `ModelCaption.model_version = \"<provider>/<prompt_template_version>\"`
(예: \"ollama/caption-v1\") — prompt 또는 모델 회귀 감사 가능.
## kebab-core / kebab-llm-local 변경
- `kebab_core::GenerateRequest` 에 `images: Vec<String>` 필드 추가.
`#[serde(default)]` 으로 기존 wire 페이로드 / snapshot 호환.
- `kebab-llm-local::OllamaLanguageModel` 가 req.images 를 Ollama
`images: [base64, ...]` 와이어 필드로 라우팅.
`#[serde(skip_serializing_if = is_empty)]` 로 비어 있을 때 wire
shape 가 pre-P6-3 와 byte-identical.
## kebab-config
- 신규 `ImageCfg.caption: CaptionCfg`:
- `enabled: bool` (default false)
- `max_pixels: u32` (default 768, 클램프 [128, 1536])
- `prompt_template_version: String` (default \"caption-v1\")
- `KEBAB_IMAGE_CAPTION_{ENABLED,MAX_PIXELS,PROMPT_TEMPLATE_VERSION}`
3종 환경변수 추가.
## Spec deviations
`tasks/HOTFIXES.md` 2026-05-02 항목 추가:
- Symptom 1: spec p6-3 시그니처가 `&dyn LanguageModel` 인데 frozen
trait + GenerateRequest 가 vision 미지원. → trait 확장.
- Symptom 2: spec 의 cargo feature `caption` (default OFF at compile
time) → runtime gate 1개로 통합. base64/image/kebab-llm 외 추가
deps 없어 cargo feature 의 binary 절감 가치 미미.
p4-1 / p4-2 / p6-3 spec 의 amends 명시.
## 테스트
`cargo test -p kebab-parse-image --test caption` — 9건 + 1 ignored:
- feature gate (disabled → no-op / Err on direct call)
- happy path (block.caption Some + Provenance CaptionApplied)
- 빈 토큰 stream → empty text + caption.is_some()
- CapturingMock 으로 req.images 라우팅 검증 (base64 1개, decode 가능)
- 한국어 / 영어 프롬프트 분기 (CapturingMock 의 system 캡처)
- LM Err → block.caption None 유지 + events 미기록
- 결정성 (동일 mock 입력 → 동일 caption)
- max_pixels 클램프 (99999 → 1536, 4000×3000 PNG 다운스케일 검증)
- opt-in 통합 (실 192.168.0.47 Ollama / gemma4:e4b → \"The image is
a solid red color.\" 검증 완료, 4.3초)
`cargo test --workspace --no-fail-fast -j 1` 전체 pass.
`cargo clippy --workspace --all-targets -- -D warnings` pass.
## 의존성 경계
- 추가 deps: `kebab-llm` (trait 만), `base64` (이미 P6-2 에서 추가).
- dev-deps: `kebab-llm/mock` 으로 `MockLanguageModel`,
`kebab-llm-local` (통합 테스트 전용 — 런타임 deps 에는 없음).
- forbidden 침범 없음: `kebab-source-fs / parse-md / normalize /
chunk / store-* / embed* / search / rag / UI` 미참조.
contract: docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
sections: §3.4 ImageRefBlock.caption, §3.7a ModelCaption, §9.1
caption (model-generated, low trust).
58 lines
2.6 KiB
TOML
58 lines
2.6 KiB
TOML
[package]
|
|
name = "kebab-parse-image"
|
|
version = { workspace = true }
|
|
edition = { workspace = true }
|
|
rust-version = { workspace = true }
|
|
license = { workspace = true }
|
|
repository = { workspace = true }
|
|
description = "Image extractor + EXIF + OCR (Ollama-vision) for the kebab pipeline (P6-1, P6-2)"
|
|
|
|
[dependencies]
|
|
kebab-core = { path = "../kebab-core" }
|
|
kebab-config = { path = "../kebab-config" }
|
|
# `kebab-llm` re-exports the trait crate (`kebab-core::LanguageModel`)
|
|
# under a stable surface; the caption adapter consumes any
|
|
# `dyn LanguageModel`. We do NOT depend on `kebab-llm-local` (forbidden
|
|
# by p6-3 design §8) — the trait abstraction is exactly what spec
|
|
# requires.
|
|
kebab-llm = { path = "../kebab-llm" }
|
|
anyhow = { workspace = true }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
time = { workspace = true }
|
|
tracing = { workspace = true }
|
|
# `image` ships a wide format menagerie under default features (BMP, DDS,
|
|
# Farbfeld, …). We only need PNG / JPEG / WebP / GIF / TIFF for v1 (per
|
|
# task spec out-of-scope HEIC/RAW). Trim defaults to keep the dep
|
|
# closure small.
|
|
image = { version = "0.25", default-features = false, features = ["png", "jpeg", "webp", "gif", "tiff"] }
|
|
# kamadak-exif: pure-Rust EXIF reader. Used for the whitelisted tag
|
|
# extraction (DateTimeOriginal, GPS, Make, Model, Orientation, Software).
|
|
kamadak-exif = "0.6"
|
|
# Ollama-vision OCR adapter (P6-2) talks HTTP directly. We keep the
|
|
# feature surface identical to `kebab-llm-local` (blocking + json +
|
|
# rustls-tls) so both crates share the same TLS backend and the
|
|
# transitive tokio runtime is brought in once.
|
|
reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls"] }
|
|
base64 = "0.22"
|
|
|
|
[dev-dependencies]
|
|
tempfile = { workspace = true }
|
|
blake3 = { workspace = true }
|
|
# Shared test infrastructure with `kebab-llm-local`: wiremock under
|
|
# tokio for HTTP fixtures.
|
|
wiremock = { workspace = true }
|
|
tokio = { workspace = true, features = ["rt-multi-thread"] }
|
|
# Used by `tests/common/mod.rs` to render the opt-in OCR integration
|
|
# fixture. Only loaded for tests; the production crate doesn't need
|
|
# font rendering.
|
|
ab_glyph = "0.2"
|
|
base64 = "0.22"
|
|
# `kebab-llm/mock` exposes `MockLanguageModel` for hermetic caption
|
|
# tests. Real adapters (Ollama) live in `kebab-llm-local`, which is
|
|
# only allowed at the dev-dep level here — the runtime crate stays
|
|
# trait-only, so the §8 forbidden-deps rule (no `kebab-llm-local`
|
|
# at runtime) is preserved.
|
|
kebab-llm = { path = "../kebab-llm", features = ["mock"] }
|
|
kebab-llm-local = { path = "../kebab-llm-local" }
|