fix(analysis): bound concurrent OCR inferences with a shared semaphore

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/src/app.rs

@@ -443,11 +443,19 @@ async fn spawn_analysis_daemon(
                 cfg.ocr_max_decode_pixels,
             )
             .context("build ocrs engine")?;
+            // Cap concurrent CPU-bound OCR runs across all workers so a high
+            // ANALYSIS_WORKERS can't oversubscribe the blocking pool.
+            let cores = std::thread::available_parallelism()
+                .map(|n| n.get())
+                .unwrap_or(1);
+            let permits =
+                crate::analysis::ocr::ocr_concurrency_limit(cfg.workers, cores);
             let dispatcher = Arc::new(crate::analysis::ocr::OcrAnalyzeDispatcher {
                 db: db.clone(),
                 storage,
                 engine: Arc::new(engine),
                 max_image_bytes: cfg.max_image_bytes,
+                ocr_permits: Arc::new(tokio::sync::Semaphore::new(permits)),
             });
             // In-process engine is always ready — no gate.
             (dispatcher, None)