Allow Jellyfin tag context in captions

scene_search/captioner.py

@@ -56,8 +56,15 @@ class OllamaCaptioner:
         self.max_tokens = max_tokens
         self.session = requests.Session()
 
-    def caption(self, image_path: Path) -> str:
+    def caption(self, image_path: Path, context_hint: str | None = None) -> str:
         image_b64 = base64.b64encode(image_path.read_bytes()).decode("ascii")
+        prompt = self.prompt
+        if context_hint:
+            prompt = (
+                f"{prompt}\n\nMetadata context for this video: {context_hint}\n"
+                "Use this only as a vocabulary/context hint. Do not claim a tagged "
+                "detail is visible unless it is actually visible in the frame."
+            )
         response = self.session.post(
             f"{self.url}/api/chat",
             json={
@@ -66,7 +73,7 @@ class OllamaCaptioner:
                 "messages": [
                     {
                         "role": "user",
-                        "content": self.prompt,
+                        "content": prompt,
                         "images": [image_b64],
                     }
                 ],