feat(kebab-app): p9-fb-23 task 5 — stamp chunker + embedding versions on CanonicalDocument before put_document

All three ingest flows (markdown, image, pdf) now set
last_chunker_version and last_embedding_version on the CanonicalDocument
before calling put_document, giving Task 7's skip detection the data it
needs on the second run. No skip path is added yet.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

crates/kebab-app/src/lib.rs

@@ -781,7 +781,7 @@ fn ingest_one_asset(
         .map(|w| format!("{:?}: {}", w.kind, w.note))
         .collect();
 
-    let canonical = build_canonical_document(
+    let mut canonical = build_canonical_document(
         asset,
         metadata,
         parsed_blocks,
@@ -794,6 +794,13 @@ fn ingest_one_asset(
         .chunk(&canonical, chunk_policy)
         .context("kb-chunk::MdHeadingV1Chunker::chunk")?;
 
+    // Stamp chunker + embedding versions so Task 7's skip detection has
+    // data on the second run.
+    canonical.last_chunker_version = Some(MdHeadingV1Chunker.chunker_version());
+    if let Some(emb) = embedder {
+        canonical.last_embedding_version = Some(emb.model_version());
+    }
+
     // Persist. Each `put_*` call wraps its own short transaction
     // (per-document tx semantics per design §5.8); composing them is
     // the kb-app job. A failure mid-way leaves the DB in a state the
@@ -1030,6 +1037,12 @@ fn ingest_one_image_asset(
         .context("kb-chunk::MdHeadingV1Chunker::chunk (image)")?;
 
     // 5. Persist + embed — identical sequence to markdown.
+    // Stamp chunker + embedding versions (image uses MdHeadingV1Chunker
+    // for its single-block doc, so we record that version).
+    canonical.last_chunker_version = Some(MdHeadingV1Chunker.chunker_version());
+    if let Some(emb) = embedder {
+        canonical.last_embedding_version = Some(emb.model_version());
+    }
     purge_vector_orphans_for_workspace_path(app, asset, vector_store)?;
     app.sqlite
         .put_asset_with_bytes(asset, &bytes)
@@ -1244,7 +1257,7 @@ fn ingest_one_pdf_asset(
         workspace_root: &workspace_root,
         config: &extract_config,
     };
-    let canonical = PdfTextExtractor::new()
+    let mut canonical = PdfTextExtractor::new()
         .extract(&ctx, &bytes)
         .context("kb-parse-pdf::PdfTextExtractor::extract")?;
 
@@ -1257,6 +1270,13 @@ fn ingest_one_pdf_asset(
         .chunk(&canonical, chunk_policy)
         .context("kb-chunk::PdfPageV1Chunker::chunk")?;
 
+    // Stamp chunker + embedding versions so Task 7's skip detection has
+    // data on the second run.
+    canonical.last_chunker_version = Some(chunker.chunker_version());
+    if let Some(emb) = embedder {
+        canonical.last_embedding_version = Some(emb.model_version());
+    }
+
     purge_vector_orphans_for_workspace_path(app, asset, vector_store)?;
     app.sqlite
         .put_asset_with_bytes(asset, &bytes)

crates/kebab-app/tests/ingest_lexical.rs

@@ -218,3 +218,41 @@ fn inspect_chunk_not_found_returns_actionable_error() {
     let msg = format!("{err:#}");
     assert!(msg.contains("not found"), "got: {msg}");
 }
+
+/// p9-fb-23 task 5: every freshly-ingested markdown doc must carry
+/// `last_chunker_version`. With `provider="none"` (lexical-only),
+/// `last_embedding_version` stays `None`.
+#[test]
+fn ingest_stamps_chunker_version_on_document() {
+    let env = TestEnv::lexical_only();
+    let report =
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    assert!(report.new >= 1, "expected at least one new doc: {report:?}");
+    assert_eq!(report.errors, 0, "no errors expected: {report:?}");
+
+    let docs = kebab_app::list_docs_with_config(
+        env.config.clone(),
+        kebab_core::DocFilter::default(),
+    )
+    .unwrap();
+    assert!(!docs.is_empty(), "no docs after ingest");
+
+    for doc_entry in &docs {
+        let canonical =
+            kebab_app::inspect_doc_with_config(env.config.clone(), &doc_entry.doc_id)
+                .unwrap();
+        assert!(
+            canonical.last_chunker_version.is_some(),
+            "last_chunker_version must be stamped for doc {}: got {:?}",
+            doc_entry.doc_id.0,
+            canonical.last_chunker_version,
+        );
+        // provider="none" → embedder is None → last_embedding_version stays None.
+        assert!(
+            canonical.last_embedding_version.is_none(),
+            "last_embedding_version must be None when provider=none for doc {}: got {:?}",
+            doc_entry.doc_id.0,
+            canonical.last_embedding_version,
+        );
+    }
+}