feat(events): Wire resource event fetching into sync pipeline (bd-1ep)

Enqueue resource_events jobs for all issues/MRs after discussion sync,
then drain the queue by fetching state/label/milestone events from GitLab
API and storing them via transaction-based wrappers. Adds progress events,
count tracking through orchestrator->ingest->sync result chain, and
respects fetch_resource_events config flag. Includes clippy fixes across
codebase from parallel agent work.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Taylor Eernisse
2026-02-03 12:51:49 -05:00
parent 5c521491b7
commit 128008578a
47 changed files with 1981 additions and 653 deletions

View File

@@ -102,7 +102,10 @@ fn knn_search_returns_nearest_neighbors() {
let results = lore::search::search_vector(&conn, &query, 10).unwrap();
assert!(!results.is_empty(), "Should return at least one result");
assert_eq!(results[0].document_id, 1, "Nearest neighbor should be doc 1");
assert_eq!(
results[0].document_id, 1,
"Nearest neighbor should be doc 1"
);
}
#[test]
@@ -122,7 +125,12 @@ fn knn_search_respects_limit() {
fn knn_search_deduplicates_chunks() {
let (_tmp, conn) = create_test_db();
insert_document(&conn, 1, "Multi-chunk doc", "Very long content that was chunked.");
insert_document(
&conn,
1,
"Multi-chunk doc",
"Very long content that was chunked.",
);
// Same document, two chunks, both similar to query
let mut v1 = vec![0.0f32; 768];
@@ -137,7 +145,8 @@ fn knn_search_deduplicates_chunks() {
let results = lore::search::search_vector(&conn, &axis_vector(0), 10).unwrap();
// Should deduplicate: same document_id appears at most once
let unique_docs: std::collections::HashSet<i64> = results.iter().map(|r| r.document_id).collect();
let unique_docs: std::collections::HashSet<i64> =
results.iter().map(|r| r.document_id).collect();
assert_eq!(
unique_docs.len(),
results.len(),
@@ -154,22 +163,38 @@ fn orphan_trigger_deletes_embeddings_on_document_delete() {
// Verify embedding exists
let count: i64 = conn
.query_row("SELECT COUNT(*) FROM embeddings WHERE rowid = 1000", [], |r| r.get(0))
.query_row(
"SELECT COUNT(*) FROM embeddings WHERE rowid = 1000",
[],
|r| r.get(0),
)
.unwrap();
assert_eq!(count, 1, "Embedding should exist before delete");
// Delete the document
conn.execute("DELETE FROM documents WHERE id = 1", []).unwrap();
conn.execute("DELETE FROM documents WHERE id = 1", [])
.unwrap();
// Verify embedding was cascade-deleted via trigger
let count: i64 = conn
.query_row("SELECT COUNT(*) FROM embeddings WHERE rowid = 1000", [], |r| r.get(0))
.query_row(
"SELECT COUNT(*) FROM embeddings WHERE rowid = 1000",
[],
|r| r.get(0),
)
.unwrap();
assert_eq!(count, 0, "Trigger should delete embeddings when document is deleted");
assert_eq!(
count, 0,
"Trigger should delete embeddings when document is deleted"
);
// Verify metadata was cascade-deleted via FK
let meta_count: i64 = conn
.query_row("SELECT COUNT(*) FROM embedding_metadata WHERE document_id = 1", [], |r| r.get(0))
.query_row(
"SELECT COUNT(*) FROM embedding_metadata WHERE document_id = 1",
[],
|r| r.get(0),
)
.unwrap();
assert_eq!(meta_count, 0, "Metadata should be cascade-deleted");
}
@@ -206,7 +231,8 @@ fn overflow_doc_with_error_sentinel_not_re_detected_as_pending() {
.unwrap();
// Now find_pending_documents should NOT return this document
let pending = lore::embedding::find_pending_documents(&conn, 100, 0, "nomic-embed-text").unwrap();
let pending =
lore::embedding::find_pending_documents(&conn, 100, 0, "nomic-embed-text").unwrap();
assert!(
pending.is_empty(),
"Document with overflow error sentinel should not be re-detected as pending, got {} pending",
@@ -215,7 +241,10 @@ fn overflow_doc_with_error_sentinel_not_re_detected_as_pending() {
// count_pending_documents should also return 0
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
assert_eq!(count, 0, "Count should be 0 for document with overflow sentinel");
assert_eq!(
count, 0,
"Count should be 0 for document with overflow sentinel"
);
}
#[test]
@@ -226,14 +255,24 @@ fn count_and_find_pending_agree() {
// Case 1: No documents at all
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
let found = lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(count as usize, found.len(), "Empty DB: count and find should agree");
let found =
lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(
count as usize,
found.len(),
"Empty DB: count and find should agree"
);
// Case 2: New document (no metadata)
insert_document(&conn, 1, "New doc", "Content");
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
let found = lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(count as usize, found.len(), "New doc: count and find should agree");
let found =
lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(
count as usize,
found.len(),
"New doc: count and find should agree"
);
assert_eq!(count, 1);
// Case 3: Document with matching metadata (not pending)
@@ -247,8 +286,13 @@ fn count_and_find_pending_agree() {
)
.unwrap();
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
let found = lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(count as usize, found.len(), "Complete doc: count and find should agree");
let found =
lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(
count as usize,
found.len(),
"Complete doc: count and find should agree"
);
assert_eq!(count, 0);
// Case 4: Config drift (chunk_max_bytes mismatch)
@@ -258,8 +302,13 @@ fn count_and_find_pending_agree() {
)
.unwrap();
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
let found = lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(count as usize, found.len(), "Config drift: count and find should agree");
let found =
lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
assert_eq!(
count as usize,
found.len(),
"Config drift: count and find should agree"
);
assert_eq!(count, 1);
}