Fix image search: embed markdown instead of describing URLs

- tools.py: search_images result now includes 'embed' (ready-to-use
  markdown image syntax) and 'citation' fields instead of raw 'local_url';
  adds 'instructions' field so the model knows to render them verbatim
- llm.py: system prompt now explicitly tells the model to embed images
  using the 'embed' field rather than describing or listing URLs
- markdown.ts: explicitly allow src/alt in PURIFY_OPTS_FULL so img tags
  are never stripped by DOMPurify

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

frontend/src/utils/markdown.ts

@@ -37,7 +37,7 @@ const headingRenderer = {
 marked.use({ renderer: headingRenderer });
 
 const PURIFY_OPTS_FULL = {
-  ADD_ATTR: ["data-tag", "data-title"],
+  ADD_ATTR: ["data-tag", "data-title", "src", "alt"],
   FORCE_BODY: true,
 };
 

src/fabledassistant/services/llm.py

@@ -398,6 +398,11 @@ async def build_context(
         tool_lines.append("Use search_todos to find a specific CalDAV todo by keyword when list_todos would return too many results.")
     tool_lines.append("For relative dates like 'Friday' or 'next week', resolve them to YYYY-MM-DD format.")
     tool_lines.append("When creating notes, use the `tags` parameter — do not embed #tag text in the note body.")
+    tool_lines.append(
+        "When search_images returns results, embed each image directly in your response by writing "
+        "the 'embed' field verbatim (e.g. ![Cat](/api/images/3)), then the 'citation' field on the "
+        "next line. Never describe images as text or list their URLs — always render them as markdown images."
+    )
     tool_lines.append(
         "Use update_note to edit/expand an existing note OR to update a task's status/priority/due_date. "
         "Use create_note ONLY for genuinely new notes with a different title. "

src/fabledassistant/services/tools.py

@@ -1264,18 +1264,28 @@ async def execute_tool(user_id: int, tool_name: str, arguments: dict) -> dict:
                     source_domain=r.get("source_domain"),
                 )
                 if record:
+                    title = record.title or query
+                    page_url = r.get("page_url", "")
+                    source_domain = r.get("source_domain", "")
                     images.append({
-                        "local_url": f"/api/images/{record.id}",
+                        "embed": f"![{title}](/api/images/{record.id})",
-                        "page_url": r.get("page_url", ""),
+                        "citation": f"*Source: [{source_domain or 'image'}]({page_url})*",
-                        "source_domain": r.get("source_domain", ""),
+                        "page_url": page_url,
-                        "title": record.title or query,
+                        "title": title,
                     })
             if not images:
                 return {"success": False, "error": f"Could not retrieve images for '{query}'"}
             return {
                 "success": True,
                 "type": "image_search",
-                "data": {"query": query, "images": images},
+                "data": {
+                    "query": query,
+                    "images": images,
+                    "instructions": (
+                        "Embed each image in your response by writing the 'embed' field verbatim, "
+                        "then the 'citation' field on the next line. Do not paraphrase or list URLs."
+                    ),
+                },
             }
 
         else: