Fix Gemini candidate cap causing search 500s

2026-03-13 19:40:30 +09:00
parent e4262613c3
commit d8cc32e2e7
3 changed files with 18 additions and 1 deletions
@@ -117,6 +117,17 @@
  - new service layer file: `backend/services/ranker.go`
  - handler is now thinner and less coupled to search internals

+## Current Session Update (2026-03-13, 500 Fix)
+- A server-side `request failed (500)` regression was found after the ranker split.
+- Root cause:
+  - Gemini candidate cap logic returned `12` even when only `9` ranked candidates existed
+  - Gemini batch slicing then attempted to read beyond the available slice bounds
+- Fix applied:
+  - `GeminiCandidateLimit` now never exceeds the real candidate count for totals up to 12
+  - Gemini evaluation now stays within valid ranked slice bounds
+- Effect:
+  - avoids backend 500 during the Gemini Vision evaluation stage for mid-sized result sets
+
 ## Local Self-Test Workflow
 - Primary command:
  - `bash scripts/selftest.sh`