P5b review: background embedder re-queues a failed document and waits for a busy gate; no empty vectors cached

Owner review of p5b (tasks 01-03 by Ornith):
- background.go: `seen` was never cleared, so a document whose background embedding failed
  (Dixie hiccup) or was abandoned could never be queued again: every later question on it stayed
  BM25 for the life of the process. Dedupe now covers only queued and in-progress documents.
- background.go: acquireGate gave up after one retry and dropped the document; the task said to
  keep retrying once a second. It now waits (background work has no deadline).
- retrieval.go/background.go: a vector the server left out is not cached as an empty vector.
- bm25.go: Scores on a nil *BM25 dereferenced it; returns nil.
Regression tests in review_test.go; both fail on the old code.

End-to-end against Dixie (local serve): Karpathy's thesis, 95 pages / 51 chunks: bm25 in 19 s,
hybrid (51 embedded) after the background; RP2040 datasheet, 642 pages / 284 chunks (a 422
before P5b): bm25 in 13.5 s, all 284 embedded within 90 s, hybrid answer correct with its quote.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

internal/digest/retrieval.go

@@ -51,7 +51,9 @@ func (e *Engine) hybridOrBM25(ctx context.Context, chunks []string, question, co
 			return joinBudget(chunks, SmallDoc), min(len(chunks), countBudget(chunks, SmallDoc)), len(chunks), "hybrid", len(cached), err
 		}
 		for j, i := range uncached {
-			e.Cache.PutEmbed(key(i), vecs[j+1])
+			if len(vecs[j+1]) > 0 { // a vector the server left out is not cached as empty
+				e.Cache.PutEmbed(key(i), vecs[j+1])
+			}
 		}
 		chunkVecs := make([][]float64, len(chunks))
 		for k, i := range cached {