test(ingest): config invalidation e2e + parser_version assert 갱신

- config_invalidation.rs(신규): 동일config=전skip / 청킹변경=md+code재색인 /
  [ingest.code]변경=코드만 / search변경=재색인0 (회귀가드) end-to-end.
- code_ingest_smoke / pdf_pipeline: 저장 parser_version 이 이제
  "{base}|{sig}" composite 라, exact assert 를 base 접두사(split('|').next()) 비교로 갱신.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

crates/kebab-app/tests/code_ingest_smoke.rs

@@ -52,7 +52,9 @@ fn rust_file_ingests_and_searches_as_code_citation() {
         "at least one chunk expected: {code_item:?}"
     );
     assert_eq!(
-        code_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        code_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-rust-v1"),
         "parser_version must be code-rust-v1"
     );
@@ -185,7 +187,9 @@ fn python_file_ingests_and_searches_as_code_citation() {
         .find(|i| i.doc_path.0.ends_with("metrics.py"))
         .expect("metrics.py item");
     assert_eq!(
-        py_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        py_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-python-v1"),
         "parser_version must be code-python-v1"
     );
@@ -261,7 +265,9 @@ fn typescript_file_ingests_and_searches_as_code_citation() {
         .find(|i| i.doc_path.0.ends_with("Foo.ts"))
         .expect("Foo.ts item");
     assert_eq!(
-        ts_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        ts_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-ts-v1"),
         "parser_version must be code-ts-v1"
     );
@@ -337,7 +343,9 @@ fn javascript_file_ingests_and_searches_as_code_citation() {
         .find(|i| i.doc_path.0.ends_with("Bar.js"))
         .expect("Bar.js item");
     assert_eq!(
-        js_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        js_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-js-v1"),
         "parser_version must be code-js-v1"
     );
@@ -415,7 +423,9 @@ fn go_file_ingests_and_searches_as_code_citation() {
         .find(|i| i.doc_path.0.ends_with("ast.go"))
         .expect("ast.go item present");
     assert_eq!(
-        go_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        go_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-go-v1"),
         "parser_version must be code-go-v1"
     );
@@ -486,7 +496,9 @@ fn java_file_ingests_and_searches_as_code_citation() {
         .find(|i| i.doc_path.0.ends_with("Foo.java"))
         .expect("Foo.java item present");
     assert_eq!(
-        java_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        java_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-java-v1"),
         "parser_version must be code-java-v1"
     );
@@ -561,7 +573,9 @@ fn kotlin_file_ingests_and_searches_as_code_citation() {
         .find(|i| i.doc_path.0.ends_with("Foo.kt"))
         .expect("Foo.kt item present");
     assert_eq!(
-        kt_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        kt_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-kotlin-v1"),
         "parser_version must be code-kotlin-v1"
     );
@@ -634,7 +648,9 @@ fn tier2_k8s_yaml_ingest_searchable() {
         .find(|i| i.doc_path.0.ends_with("deploy.yaml"))
         .expect("deploy.yaml item present");
     assert_eq!(
-        yaml_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        yaml_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("none-v1"),
         "parser_version must be none-v1"
     );
@@ -717,7 +733,9 @@ fn tier2_dockerfile_ingest_searchable() {
         .find(|i| i.doc_path.0.ends_with("Dockerfile"))
         .expect("Dockerfile item present");
     assert_eq!(
-        df_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        df_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("none-v1"),
         "parser_version must be none-v1"
     );
@@ -800,7 +818,9 @@ fn tier2_cargo_toml_ingest_searchable() {
         .find(|i| i.doc_path.0.ends_with("Cargo.toml"))
         .expect("Cargo.toml item present");
     assert_eq!(
-        toml_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        toml_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("none-v1"),
         "parser_version must be none-v1"
     );
@@ -883,7 +903,9 @@ fn tier3_shell_ingest_searchable() {
         .find(|i| i.doc_path.0.ends_with("deploy.sh"))
         .expect("deploy.sh item present");
     assert_eq!(
-        sh_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        sh_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("none-v1"),
         "parser_version must be none-v1 for shell (Tier 3 direct)"
     );
@@ -974,7 +996,9 @@ fn tier3_yaml_fallback_picks_up_non_k8s_yaml() {
         .find(|i| i.doc_path.0.ends_with("docker-compose.yml"))
         .expect("docker-compose.yml item present");
     assert_eq!(
-        yaml_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        yaml_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("none-v1"),
         "parser_version must be none-v1 after Tier 3 fallback"
     );
@@ -1144,7 +1168,9 @@ fn tier1_c_ingest_searchable() {
         .find(|i| i.doc_path.0.ends_with("parser.c"))
         .expect("parser.c item present");
     assert_eq!(
-        c_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        c_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-c-v2"),
         "parser_version must be code-c-v2 (v0.17.0 PR-B: typedef-wrapped struct/enum/union 이 typedef alias unit 으로 방출)"
     );
@@ -1228,7 +1254,9 @@ fn tier1_cpp_ingest_searchable() {
         .find(|i| i.doc_path.0.ends_with("chunker.cpp"))
         .expect("chunker.cpp item present");
     assert_eq!(
-        cpp_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        cpp_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("code-cpp-v1"),
         "parser_version must be code-cpp-v1"
     );

crates/kebab-app/tests/config_invalidation.rs

@@ -0,0 +1,148 @@
+//! v0.26.2: ingest-config invalidation — changing a setting that affects
+//! ingest output auto-re-indexes the affected assets on the next ingest
+//! (no `--force-reingest`), while changing an unrelated setting does not.
+//!
+//! These end-to-end tests exercise the model-free signals (chunking +
+//! `[ingest.code]` options vs `search` settings). The exhaustive per-setting
+//! mapping (image OCR / caption, pdf.ocr, code options, search/rag/ui
+//! invariance) is unit-tested in
+//! `kebab-app/src/lib.rs::ingest_config_signature_tests` — those toggles
+//! (OCR/caption) require a live vision endpoint to ingest, so the wiring is
+//! verified here via the signature-driven chunking path that shares the same
+//! `effective_parser_version` plumbing.
+
+mod common;
+
+use common::TestEnv;
+
+use kebab_app::{IngestOpts, ingest_with_config, ingest_with_config_opts};
+use kebab_core::IngestItemKind;
+
+/// Seed a workspace with a markdown + a rust file so both the markdown and
+/// the code ingest paths are exercised. Returns the first-ingest report.
+fn seed_and_first_ingest(env: &TestEnv) -> kebab_core::IngestReport {
+    std::fs::write(
+        env.workspace_root.join("demo.rs"),
+        "/// adds two integers\npub fn add(a: i32, b: i32) -> i32 {\n    a + b\n}\n",
+    )
+    .unwrap();
+    let first = ingest_with_config(env.config.clone(), env.scope(), false).expect("first ingest");
+    assert_eq!(first.errors, 0, "first ingest must not error: {first:?}");
+    assert!(first.new >= 1, "first ingest creates docs: {first:?}");
+    assert_eq!(first.unchanged, 0, "first ingest has no unchanged: {first:?}");
+    first
+}
+
+fn reingest(env: &TestEnv) -> kebab_core::IngestReport {
+    ingest_with_config_opts(env.config.clone(), env.scope(), false, IngestOpts::default())
+        .expect("re-ingest")
+}
+
+/// Re-running with the identical config skips every asset (no spurious
+/// re-index). Regression guard for over-invalidation.
+#[test]
+fn identical_config_skips_all_assets() {
+    let env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(second.new, 0, "no new docs: {second:?}");
+    assert_eq!(second.updated, 0, "nothing re-indexed: {second:?}");
+    assert_eq!(second.unchanged, scanned, "every doc Unchanged: {second:?}");
+    assert_eq!(second.errors, 0);
+}
+
+/// Changing a common chunking parameter re-indexes EVERY media type
+/// (markdown + code here) without `--force-reingest`.
+#[test]
+fn chunking_change_reindexes_all_types() {
+    let mut env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    // Bump target_tokens — folds into every type's signature.
+    env.config.chunking.target_tokens += 100;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(second.new, 0, "no new docs: {second:?}");
+    assert_eq!(
+        second.unchanged, 0,
+        "chunking change must re-index all: {second:?}"
+    );
+    assert_eq!(
+        second.updated, scanned,
+        "every doc re-indexed as Updated: {second:?}"
+    );
+    assert_eq!(second.errors, 0);
+}
+
+/// Changing an `[ingest.code]` option re-indexes only the code asset; the
+/// markdown assets stay Unchanged.
+#[test]
+fn code_option_change_reindexes_code_only() {
+    let mut env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    // Raise max_file_lines (keeps the tiny demo.rs in-scope; only the code
+    // signature changes).
+    env.config.ingest.code.max_file_lines += 1000;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(second.new, 0, "no new docs: {second:?}");
+    assert_eq!(second.errors, 0);
+    assert_eq!(
+        second.updated, 1,
+        "exactly the code asset re-indexed: {second:?}"
+    );
+    assert_eq!(
+        second.unchanged,
+        scanned - 1,
+        "all markdown assets stay Unchanged: {second:?}"
+    );
+
+    let items = second.items.as_ref().expect("items present");
+    let code = items
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("demo.rs"))
+        .expect("demo.rs item");
+    assert_eq!(
+        code.kind,
+        IngestItemKind::Updated,
+        "demo.rs must be re-indexed: {code:?}"
+    );
+    for i in items.iter().filter(|i| i.doc_path.0.ends_with(".md")) {
+        assert_eq!(
+            i.kind,
+            IngestItemKind::Unchanged,
+            "markdown must be Unchanged: {i:?}"
+        );
+    }
+}
+
+/// Regression guard: changing a non-ingest setting (`search.default_k`) does
+/// NOT re-index anything.
+#[test]
+fn search_setting_change_reindexes_nothing() {
+    let mut env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    env.config.search.default_k += 5;
+    env.config.search.snippet_chars += 50;
+    env.config.rag.score_gate = 0.5;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(
+        second.unchanged, scanned,
+        "search/rag changes must not re-index: {second:?}"
+    );
+    assert_eq!(second.updated, 0, "nothing re-indexed: {second:?}");
+    assert_eq!(second.new, 0);
+    assert_eq!(second.errors, 0);
+}

crates/kebab-app/tests/pdf_pipeline.rs

@@ -162,7 +162,9 @@ fn ingest_3_page_pdf_produces_one_doc_and_per_page_chunks() {
         "one chunk per non-empty page"
     );
     assert_eq!(
-        pdf_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        pdf_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("pdf-text-v1")
     );
     assert_eq!(
@@ -477,7 +479,10 @@ fn inspect_doc_surfaces_page_spans() {
         .find(|i| i.doc_path.0.ends_with("inspect.pdf"))
         .unwrap();
     let doc = kebab_app::inspect_doc_with_config(cfg, pdf_item.doc_id.as_ref().unwrap()).unwrap();
-    assert_eq!(doc.parser_version.0, "pdf-text-v1");
+    // v0.26.2: stored parser_version is now `pdf-text-v1|<ingest-config-sig>`
+    // (the signature folds chunking / pdf.ocr settings for skip detection).
+    // Assert the base identity by taking the prefix before the first '|'.
+    assert_eq!(doc.parser_version.0.split('|').next().unwrap(), "pdf-text-v1");
     assert_eq!(doc.blocks.len(), 3);
     for block in &doc.blocks {
         match block {