feat: parallelize lookup (Wiki+SearXNG) and include Wikipedia thumbnails

Runs the Wikipedia summary and SearXNG search concurrently and returns
both when available, so current-event questions aren't masked by a
generic role article from Wikipedia. When the Wikipedia summary includes
a thumbnail, it is cached through the existing image pipeline and
surfaced as an embeddable markdown snippet alongside the extract.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/fabledassistant/services/tools/web.py

@@ -23,57 +23,91 @@ logger = logging.getLogger(__name__)
     required=["query"],
 )
 async def lookup_tool(*, user_id, arguments, **_ctx):
+    import asyncio
+
     from fabledassistant.config import Config
     from fabledassistant.services.wikipedia import wiki_summary
 
-    query = arguments.get("query", "")
+    query = arguments.get("query", "").strip()
+    if not query:
+        return {"success": False, "error": "query is required"}
 
-    # 1. Try Wikipedia first
-    wiki = await wiki_summary(query)
+    searxng_enabled = Config.searxng_enabled()
+
+    async def _searxng_results() -> list[dict]:
+        if not searxng_enabled:
+            return []
+        from fabledassistant.services.research import _search_searxng
+        return await _search_searxng(query) or []
+
+    wiki, search_results = await asyncio.gather(
+        wiki_summary(query),
+        _searxng_results(),
+    )
+
+    wiki_payload: dict | None = None
     if wiki:
+        wiki_payload = {
+            "title": wiki["title"],
+            "extract": wiki["extract"],
+            "url": wiki["url"],
+        }
+        thumb_url = wiki.get("thumbnail_url") or ""
+        if thumb_url:
+            from fabledassistant.services.images import fetch_and_store_image
+            record = await fetch_and_store_image(
+                url=thumb_url,
+                title=wiki["title"],
+                source_domain="en.wikipedia.org",
+            )
+            if record:
+                wiki_payload["image"] = {
+                    "embed": f"![{wiki['title']}](/api/images/{record.id})",
+                    "citation": f"*Source: [Wikipedia]({wiki['url']})*",
+                }
+
+    web_payload: list[dict] = []
+    if search_results:
+        from fabledassistant.services.rss import _fetch_full_article
+
+        top = [r for r in search_results[:2] if r.get("url")]
+        contents = await asyncio.gather(
+            *(_fetch_full_article(r["url"]) for r in top),
+            return_exceptions=True,
+        )
+        for r, content in zip(top, contents, strict=False):
+            content_text = content if isinstance(content, str) else ""
+            web_payload.append({
+                "url": r["url"],
+                "title": r.get("title", r["url"]),
+                "snippet": r.get("snippet", ""),
+                "content": content_text[:4000],
+            })
+
+    if not wiki_payload and not web_payload:
         return {
             "success": True,
             "type": "lookup",
-            "source": "wikipedia",
-            "data": wiki,
+            "data": {
+                "query": query,
+                "message": "No results found. You can answer from your own knowledge.",
+            },
         }
 
-    # 2. Fall back to SearXNG + article fetch
-    if Config.searxng_enabled():
-        from fabledassistant.services.research import _search_searxng
-        from fabledassistant.services.rss import _fetch_full_article
-
-        results = await _search_searxng(query)
-        if results:
-            articles: list[dict] = []
-            for r in results[:2]:
-                url = r.get("url", "")
-                if not url:
-                    continue
-                content = await _fetch_full_article(url)
-                articles.append({
-                    "url": url,
-                    "title": r.get("title", url),
-                    "snippet": r.get("snippet", ""),
-                    "content": (content or "")[:4000],
-                })
-            if articles:
-                return {
-                    "success": True,
-                    "type": "lookup",
-                    "source": "web",
-                    "data": {"query": query, "results": articles},
-                }
-
-    # 3. No sources available
+    data: dict = {
+        "query": query,
+        "wikipedia": wiki_payload,
+        "web": web_payload,
+    }
+    if wiki_payload and wiki_payload.get("image"):
+        data["image_instructions"] = (
+            "If an image is relevant to your reply, embed it by writing the wikipedia.image.embed "
+            "field verbatim, then the citation field on the next line. Otherwise omit it."
+        )
     return {
         "success": True,
         "type": "lookup",
-        "source": "none",
-        "data": {
-            "query": query,
-            "message": "No results found. You can answer from your own knowledge.",
-        },
+        "data": data,
     }
 
 

src/fabledassistant/services/wikipedia.py

@@ -12,11 +12,21 @@ _TIMEOUT = 5.0
 _USER_AGENT = "FabledAssistant/1.0 (https://fabledsword.com)"
 
 
+def _extract_thumbnail(data: dict) -> str:
+    """Prefer the 320px thumbnail (kinder to cache/bandwidth) over originalimage."""
+    thumb = data.get("thumbnail", {}).get("source", "")
+    if thumb:
+        return thumb
+    return data.get("originalimage", {}).get("source", "")
+
+
 async def wiki_summary(query: str) -> dict | None:
     """Fetch a Wikipedia summary for a given title/query.
 
     Does a direct title lookup via the REST v1 summary endpoint.
-    Returns a dict with title, extract, and url on success; None on any failure.
+    Returns a dict with title, extract, url, and thumbnail_url on success;
+    thumbnail_url is an empty string when the article has no image.
+    Returns None on any failure.
     """
     title = url_quote(query.replace(" ", "_"))
     url = f"{_SUMMARY_URL}/{title}"
@@ -37,6 +47,7 @@ async def wiki_summary(query: str) -> dict | None:
                 "title": data.get("title", query),
                 "extract": extract,
                 "url": data.get("content_urls", {}).get("desktop", {}).get("page", ""),
+                "thumbnail_url": _extract_thumbnail(data),
             }
     except Exception as exc:
         logger.debug("wiki_summary failed for %r: %s", query, exc)
@@ -91,6 +102,7 @@ async def wiki_search(query: str, limit: int = 3) -> list[dict]:
                             "url": sdata.get("content_urls", {})
                             .get("desktop", {})
                             .get("page", ""),
+                            "thumbnail_url": _extract_thumbnail(sdata),
                         }
                     )
                 except Exception as exc: