From 4cc16bc7f5bd13a73776c27527b9fbe4c52535f1 Mon Sep 17 00:00:00 2001 From: Bogdan Szabo Date: Sun, 1 Nov 2026 09:10:07 +0100 Subject: [PATCH] One embed_names job per base: a running copy counts as queued The per-document enqueue only looked at queued copies, so once the first embed_names claimed, every document extracted while it ran queued another, and on a base whose pending scan takes hours (48k identity names, deeplethe/utopia#1472) 14 copies sat behind it, each scanning the same facts. The enqueue now skips a running copy too, and the job re-enqueues itself whenever it filled anything, so names written while it ran are picked up by the next one. Refs deeplethe/utopia#1472. Co-Authored-By: Claude Fable 5.1 --- crates/utopia-server/src/extraction_open.rs | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/crates/utopia-server/src/extraction_open.rs b/crates/utopia-server/src/extraction_open.rs index 43fc2861c..248051ae2 100644 --- a/crates/utopia-server/src/extraction_open.rs +++ b/crates/utopia-server/src/extraction_open.rs @@ -937,7 +937,9 @@ pub(crate) async fn embed_names_job(state: &AppState, kb_id: Uuid) -> anyhow::Re if filled > 0 { tracing::info!(%kb_id, names = filled, "名字向量已补"); } - if i64::try_from(filled).unwrap_or(i64::MAX) >= NAME_VECTOR_PENDING { + // 补了名字就再排一份：这一份跑着时抽完的文档撞上「正在跑」不再排（见排它的那处）， + // 它们写下的名字由下一份补；一批满了更是可能还有。只排着一份，所以这最多多跑一遍空的 + if filled > 0 { utopia_store::jobs::enqueue_unless_queued( &state.pool, "embed_names", @@ -1288,12 +1290,15 @@ pub(crate) async fn run_open( } // 名字向量：这篇新写的名字事实，向量补上（0041 决定 3 通道 2）。补在一份按库去重的 // `embed_names` 任务里（#1296）：找还没有向量的名字要扫全库的名字事实，一阵推送几百篇 - // 时每篇扫一遍是推送最贵的几笔之一；排着一份就不再排，它跑一遍补上这一阵写下的名字 + // 时每篇扫一遍是推送最贵的几笔之一；排着**或正在跑**的一份就不再排——只看排着的， + // 第一份一开跑，之后抽完的每篇都再排一份，一份跑几小时时（身份名多的库，#1472） + // 十几份串在它后面各扫一遍；跑着的那份结束时若还有没补的会自己再排（`embed_names_job`） if settings.is_some() && embed.is_some() { - utopia_store::jobs::enqueue_unless_queued( + utopia_store::jobs::enqueue_unless_pending( pool, "embed_names", serde_json::json!({ "kb_id": kb_id }), + std::time::Duration::ZERO, ) .await?; }