feat(kebab-app): p9-fb-25 task 5 — Skipped warnings + skipped_by_extension aggregation

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

crates/kebab-app/src/lib.rs

@@ -384,7 +384,7 @@ pub fn ingest_with_config_opts(
     let mut chunks_indexed: u32 = 0;
     let mut embeddings_indexed: u32 = 0;
     // p9-fb-25: per-extension skip count, populated in the Skipped arm below.
-    let skipped_by_extension: std::collections::BTreeMap<String, u32> =
+    let mut skipped_by_extension: std::collections::BTreeMap<String, u32> =
         std::collections::BTreeMap::new();
     let scanned_count: u32 = u32::try_from(assets.len()).unwrap_or(u32::MAX);
 
@@ -475,7 +475,9 @@ pub fn ingest_with_config_opts(
                 }
             }
             kebab_core::IngestItemKind::Skipped => {
-                skipped_count = skipped_count.saturating_add(1)
+                skipped_count = skipped_count.saturating_add(1);
+                let ext = ext_for_skip_warning(&item.doc_path.0);
+                *skipped_by_extension.entry(ext).or_insert(0) += 1;
             }
             kebab_core::IngestItemKind::Unchanged => {
                 unchanged_count = unchanged_count.saturating_add(1)
@@ -826,6 +828,31 @@ fn try_skip_unchanged(
     }))
 }
 
+/// p9-fb-25: extract the lowercase extension (no leading dot) from a
+/// workspace path for use in the `unsupported media type: .X` warning
+/// and `IngestReport.skipped_by_extension` key. Returns `"<no-ext>"`
+/// for paths with no extension. Always lowercase so `Foo.DOCX` and
+/// `bar.docx` aggregate under the same key.
+fn ext_for_skip_warning(path: &str) -> String {
+    std::path::Path::new(path)
+        .extension()
+        .and_then(|s| s.to_str())
+        .map(|s| s.to_ascii_lowercase())
+        .unwrap_or_else(|| "<no-ext>".to_string())
+}
+
+/// p9-fb-25: render the `IngestItem.warnings` line for a Skipped
+/// asset. `<no-ext>` sentinel renders without a leading dot;
+/// everything else gets `.ext` form.
+fn unsupported_media_warning(path: &str) -> String {
+    let ext = ext_for_skip_warning(path);
+    if ext == "<no-ext>" {
+        "unsupported media type: <no-ext>".to_string()
+    } else {
+        format!("unsupported media type: .{ext}")
+    }
+}
+
 /// Process a single asset: read bytes, parse, normalize, chunk,
 /// persist, embed. Per-asset failures bubble up to the caller for
 /// labelling as `IngestItemKind::Error` — they do NOT abort the
@@ -889,7 +916,7 @@ fn ingest_one_asset(
                 chunk_count: None,
                 parser_version: None,
                 chunker_version: None,
-                warnings: Vec::new(),
+                warnings: vec![unsupported_media_warning(&asset.workspace_path.0)],
                 error: None,
             });
         }
@@ -908,9 +935,7 @@ fn ingest_one_asset(
                 chunk_count: None,
                 parser_version: None,
                 chunker_version: None,
-                warnings: vec![
-                    "kb:// source URIs are not supported by the fs ingester".into(),
-                ],
+                warnings: vec!["kb:// URI not yet supported".to_string()],
                 error: None,
             });
         }
@@ -1103,7 +1128,7 @@ fn ingest_one_image_asset(
                 parser_version: None,
                 chunker_version: None,
                 warnings: vec![
-                    "kb:// source URIs are not supported by the fs ingester".into(),
+                    "kb:// URI not yet supported".to_string(),
                 ],
                 error: None,
             });
@@ -1438,7 +1463,7 @@ fn ingest_one_pdf_asset(
                 parser_version: None,
                 chunker_version: None,
                 warnings: vec![
-                    "kb:// source URIs are not supported by the fs ingester".into(),
+                    "kb:// URI not yet supported".to_string(),
                 ],
                 error: None,
             });

crates/kebab-app/tests/skip_reason.rs

@@ -0,0 +1,43 @@
+//! p9-fb-25 task 5: skipped per-asset items must carry a human-readable
+//! reason in `warnings`, and the report's `skipped_by_extension` must
+//! aggregate by lowercase extension.
+
+mod common;
+
+use common::TestEnv;
+
+#[test]
+fn unsupported_extension_skip_carries_warning_and_is_aggregated() {
+    let env = TestEnv::lexical_only();
+    let workspace_root = std::path::PathBuf::from(&env.config.workspace.root);
+    std::fs::write(workspace_root.join("legacy.docx"), b"unsupported").unwrap();
+    std::fs::write(workspace_root.join("Makefile"), b"unsupported").unwrap();
+
+    let report = kebab_app::ingest_with_config(
+        env.config.clone(),
+        env.scope(),
+        false,
+    ).unwrap();
+
+    let items = report.items.as_ref().expect("items array populated");
+    let docx_item = items
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("legacy.docx"))
+        .expect("docx in items");
+    assert_eq!(docx_item.kind, kebab_core::IngestItemKind::Skipped);
+    assert_eq!(
+        docx_item.warnings,
+        vec!["unsupported media type: .docx".to_string()],
+    );
+    let makefile_item = items
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("Makefile"))
+        .expect("Makefile in items");
+    assert_eq!(makefile_item.kind, kebab_core::IngestItemKind::Skipped);
+    assert_eq!(
+        makefile_item.warnings,
+        vec!["unsupported media type: <no-ext>".to_string()],
+    );
+    assert_eq!(report.skipped_by_extension.get("docx").copied(), Some(1));
+    assert_eq!(report.skipped_by_extension.get("<no-ext>").copied(), Some(1));
+}