altair823-org/kebab
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 40 Wiki Activity

refactor(config): v3 경로 call-site sweep (kebab-app/kebab-eval/kebab-parse-image)

Browse Source 
부모 경로에 .ingest 삽입(leaf 구조체 불변). src + 테스트 call-site 전부.
kebab-cli 테스트의 v2 TOML fixture 는 from_file 자동변환(T6) 경로 검증용으로 유지.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
altair823
2026-06-04 12:40:06 +00:00
parent 148c8b7040
commit d5c69f6715
19 changed files with 90 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
crates/kebab-app/tests/common/mod.rs
View File

@@ -62,8 +62,8 @@ impl TestEnv {
// Drop in a small chunk policy so the fixture's small files
// emit at least a couple of chunks even with overlap_tokens
// honored.
config.chunking.target_tokens = 80;
config.chunking.overlap_tokens = 20;
config.ingest.chunking.target_tokens = 80;
config.ingest.chunking.overlap_tokens = 20;
Self {
temp,

2
crates/kebab-app/tests/config_invalidation.rs
View File

@@ -63,7 +63,7 @@ fn chunking_change_reindexes_all_types() {
let scanned = first.scanned;
// Bump target_tokens — folds into every type's signature.
env.config.chunking.target_tokens += 100;
env.config.ingest.chunking.target_tokens += 100;
let second = reingest(&env);
assert_eq!(second.scanned, scanned);

22
crates/kebab-app/tests/image_pipeline.rs
View File

@@ -34,11 +34,11 @@ fn cfg_with_image_pipeline(env: &TestEnv, mock_endpoint: &str) -> Config {
let mut cfg = env.config.clone();
// p9-fb-25: workspace.include removed; extension routing is now
// handled by extractor matching alone (no config knob).
cfg.image.ocr.enabled = true;
cfg.image.ocr.endpoint = Some(mock_endpoint.to_string());
cfg.image.ocr.model = "vision-mock:1b".to_string();
cfg.image.ocr.max_pixels = 512;
cfg.image.caption.enabled = false; // tested separately below
cfg.ingest.image.ocr.enabled = true;
cfg.ingest.image.ocr.endpoint = Some(mock_endpoint.to_string());
cfg.ingest.image.ocr.model = "vision-mock:1b".to_string();
cfg.ingest.image.ocr.max_pixels = 512;
cfg.ingest.image.caption.enabled = false; // tested separately below
cfg.models.llm.endpoint = mock_endpoint.to_string();
cfg.models.llm.model = "vision-mock:1b".to_string();
cfg
@@ -161,8 +161,8 @@ async fn ingest_image_with_ocr_and_caption_populates_both_fields() {
let env = TestEnv::lexical_only();
write_red_png(&env.workspace_root, "diagram.png");
let mut cfg = cfg_with_image_pipeline(&env, &server.uri());
cfg.image.caption.enabled = true;
cfg.image.caption.max_pixels = 384;
cfg.ingest.image.caption.enabled = true;
cfg.ingest.image.caption.max_pixels = 384;
let cfg_clone = cfg.clone();
let scope = env.scope();
@@ -270,8 +270,8 @@ async fn image_indexed_with_filename_when_ocr_and_caption_disabled() {
let mut cfg = env.config.clone();
// p9-fb-25: workspace.include removed; extension routing is now
// handled by extractor matching alone (no config knob).
cfg.image.ocr.enabled = false;
cfg.image.caption.enabled = false;
cfg.ingest.image.ocr.enabled = false;
cfg.ingest.image.caption.enabled = false;
let cfg_clone = cfg.clone();
let scope = env.scope();
@@ -334,8 +334,8 @@ async fn garbage_png_increments_errors_counter_exactly_once() {
let mut cfg = env.config.clone();
// p9-fb-25: workspace.include removed; extension routing is now
// handled by extractor matching alone (no config knob).
cfg.image.ocr.enabled = false;
cfg.image.caption.enabled = false;
cfg.ingest.image.ocr.enabled = false;
cfg.ingest.image.caption.enabled = false;
let cfg_clone = cfg.clone();
let scope = env.scope();

4
crates/kebab-app/tests/ingest_log_smoke.rs
View File

@@ -23,8 +23,8 @@ fn minimal_config(workspace: &std::path::Path, log_dir: &std::path::Path) -> Con
cfg.storage.model_dir = model_dir.to_string_lossy().into_owned();
cfg.models.embedding.provider = "none".to_string();
cfg.models.embedding.dimensions = 0;
cfg.chunking.target_tokens = 80;
cfg.chunking.overlap_tokens = 20;
cfg.ingest.chunking.target_tokens = 80;
cfg.ingest.chunking.overlap_tokens = 20;
cfg.logging = LoggingCfg {
ingest_log_enabled: true,
ingest_log_dir: log_dir.to_path_buf(),

8
crates/kebab-app/tests/ingest_pdf_ocr_smoke.rs
View File

@@ -22,8 +22,8 @@ fn ollama_endpoint() -> String {
fn make_ocr_env_real() -> TestEnv {
let mut env = TestEnv::lexical_only();
env.config.pdf.ocr.enabled = true;
env.config.pdf.ocr.endpoint = Some(ollama_endpoint());
env.config.ingest.pdf.ocr.enabled = true;
env.config.ingest.pdf.ocr.endpoint = Some(ollama_endpoint());
env.config.models.embedding.provider = "none".to_string();
let src = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
@@ -92,8 +92,8 @@ fn ocr_text_indexed_and_searchable() {
#[test]
fn ingest_with_cancel_aborts_mid_pdf() {
let mut env = TestEnv::lexical_only();
env.config.pdf.ocr.enabled = true;
env.config.pdf.ocr.endpoint = Some("http://127.0.0.1:1".to_string());
env.config.ingest.pdf.ocr.enabled = true;
env.config.ingest.pdf.ocr.endpoint = Some("http://127.0.0.1:1".to_string());
let src = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
.parent()

4
crates/kebab-app/tests/ingest_progress.rs
View File

@@ -196,9 +196,9 @@ fn pdf_ocr_progress_emits_started_finished_events() {
config.storage.data_dir = data_dir.to_string_lossy().into_owned();
config.models.embedding.provider = "none".to_string();
config.models.embedding.dimensions = 0;
config.pdf.ocr.enabled = true;
config.ingest.pdf.ocr.enabled = true;
if let Ok(endpoint) = std::env::var("KEBAB_PDF_OCR_ENDPOINT") {
config.pdf.ocr.endpoint = Some(endpoint);
config.ingest.pdf.ocr.endpoint = Some(endpoint);
}
let scope = kebab_core::SourceScope {

6
crates/kebab-app/tests/pdf_ocr_events_insert_smoke.rs
View File

@@ -49,9 +49,9 @@ async fn ingest_dual_write_doc_id_matches_ndjson() {
let result = spawn_blocking(move || {
let mut env = TestEnv::lexical_only();
// Enable PDF OCR + set up mock endpoint
env.config.pdf.ocr.enabled = true;
env.config.pdf.ocr.endpoint = Some(mock_url.clone());
env.config.pdf.ocr.model = "qwen2.5vl:3b".to_string();
env.config.ingest.pdf.ocr.enabled = true;
env.config.ingest.pdf.ocr.endpoint = Some(mock_url.clone());
env.config.ingest.pdf.ocr.model = "qwen2.5vl:3b".to_string();
// Enable ingest log
let log_dir = env.temp.path().join("logs");
std::fs::create_dir_all(&log_dir).unwrap();

4
crates/kebab-app/tests/pdf_pipeline.rs
View File

@@ -121,8 +121,8 @@ fn cfg_with_pdf(env: &TestEnv) -> Config {
// PDF ingest does not need OCR / caption / LM — leave defaults
// (ocr.enabled=false, caption.enabled=false). The image pipeline
// construction step skips both adapters.
cfg.image.ocr.enabled = false;
cfg.image.caption.enabled = false;
cfg.ingest.image.ocr.enabled = false;
cfg.ingest.image.caption.enabled = false;
cfg
}

4
crates/kebab-app/tests/schema_active_versions.rs
View File

@@ -12,8 +12,8 @@ fn minimal_config(data_dir: &std::path::Path, workspace_root: &std::path::Path)
cfg.storage.model_dir = data_dir.join("models").to_string_lossy().into_owned();
cfg.models.embedding.provider = "none".to_string();
cfg.models.embedding.dimensions = 0;
cfg.chunking.target_tokens = 80;
cfg.chunking.overlap_tokens = 20;
cfg.ingest.chunking.target_tokens = 80;
cfg.ingest.chunking.overlap_tokens = 20;
cfg
}

4
crates/kebab-app/tests/schema_report.rs
View File

@@ -14,8 +14,8 @@ fn minimal_config(data_dir: &std::path::Path, workspace_root: &std::path::Path)
config.storage.model_dir = data_dir.join("models").to_string_lossy().into_owned();
config.models.embedding.provider = "none".to_string();
config.models.embedding.dimensions = 0;
config.chunking.target_tokens = 80;
config.chunking.overlap_tokens = 20;
config.ingest.chunking.target_tokens = 80;
config.ingest.chunking.overlap_tokens = 20;
config
}