Optimize backend search and evaluation pipeline

TODO.md

@@ -255,6 +255,20 @@
   - backend debug broadcasts
 
 ## Recent Change Log
+- Date: `2026-03-16`
+- What changed:
+  - Added in-process response caching for repeated SearXNG requests and for source fetches used during Envato / Artgrid enrichment.
+  - Added in-process Gemini visual cache for fetched thumbnails and extracted preview frames so repeated candidate evaluation no longer re-downloads the same asset or reruns `ffmpeg` every time.
+  - Tightened backend tests to cover the new cache helpers.
+- Why it changed:
+  - Even after reducing query fan-out, repeated search passes and Gemini reevaluation were still paying duplicate network and media-processing cost inside the same running backend.
+- How it was verified:
+  - `go test ./...`
+  - `bash scripts/selftest.sh`
+- What is still risky or incomplete:
+  - These caches are process-local and TTL-based, so they do not survive container restarts and can still grow until expiry under heavy query diversity.
+  - Cache invalidation is intentionally simple; if upstream preview assets change rapidly, stale data can be served for a few minutes.
+
 - Date: `2026-03-16`
 - What changed:
   - Result modal layout was rebuilt to match a top `16:9` embedded viewer with bottom-left full AI note and bottom-right action panel.