diff --git a/src/fabledassistant/routes/briefing.py b/src/fabledassistant/routes/briefing.py
index 2b050a8..7b3e6da 100644
--- a/src/fabledassistant/routes/briefing.py
+++ b/src/fabledassistant/routes/briefing.py
@@ -537,10 +537,16 @@ async def discuss_article(item_id: int):
     # exchange and the conversational seed user prompt into the conversation.
     # The /news from-article route calls the same helper so behavior stays
     # byte-identical across entry points.
-    from fabledassistant.services.article_context import seed_article_discussion
+    from fabledassistant.services.article_context import (
+        EmptyArticleError,
+        seed_article_discussion,
+    )
 
     model = await get_setting(uid, "default_model", "") or ""
-    discuss_prompt = await seed_article_discussion(conv_id, item, model)
+    try:
+        discuss_prompt = await seed_article_discussion(conv_id, item, model)
+    except EmptyArticleError as e:
+        return jsonify({"error": str(e)}), 422
 
     # Reload conversation with fresh messages to build history
     conv = await get_conversation(uid, conv_id)
diff --git a/src/fabledassistant/routes/chat.py b/src/fabledassistant/routes/chat.py
index 6b81bdb..6212d57 100644
--- a/src/fabledassistant/routes/chat.py
+++ b/src/fabledassistant/routes/chat.py
@@ -521,7 +521,10 @@ async def create_conversation_from_article(item_id: int):
     from sqlalchemy import select as _select
     from fabledassistant.models import async_session as _async_session
     from fabledassistant.models.rss_feed import RssItem, RssFeed
-    from fabledassistant.services.article_context import seed_article_discussion
+    from fabledassistant.services.article_context import (
+        EmptyArticleError,
+        seed_article_discussion,
+    )
 
     uid = get_current_user_id()
 
@@ -540,7 +543,16 @@ async def create_conversation_from_article(item_id: int):
     conv = await create_conversation(uid, title=conv_title, conversation_type="chat")
 
     model = await get_setting(uid, "default_model", "") or Config.OLLAMA_MODEL
-    discuss_prompt = await seed_article_discussion(conv.id, item, model)
+    try:
+        discuss_prompt = await seed_article_discussion(conv.id, item, model)
+    except EmptyArticleError as e:
+        # Roll back the empty conversation so the user doesn't end up with a
+        # phantom entry in their chat list.
+        try:
+            await delete_conversation(uid, conv.id)
+        except Exception:
+            logger.warning("Failed to clean up empty article conversation %s", conv.id)
+        return jsonify({"error": str(e)}), 422
 
     # Reload conversation so we see the two messages the helper just added.
     conv = await get_conversation(uid, conv.id)
diff --git a/src/fabledassistant/services/article_context.py b/src/fabledassistant/services/article_context.py
index 1a41a94..79bd685 100644
--- a/src/fabledassistant/services/article_context.py
+++ b/src/fabledassistant/services/article_context.py
@@ -182,6 +182,15 @@ ARTICLE_DISCUSS_SEED = (
 )
 
 
+class EmptyArticleError(Exception):
+    """Raised when an article has no extractable body text.
+
+    Callers (the briefing and /news discuss routes) map this to a 422 so the
+    user sees a clear error instead of a hallucinated summary built from an
+    empty synthetic tool result.
+    """
+
+
 async def seed_article_discussion(
     conv_id: int,
     item: RssItem,
@@ -213,15 +222,30 @@ async def seed_article_discussion(
         article_content = item.context_prepared
     else:
         raw_body = await get_or_fetch_full_article(item) or item.content or ""
+        if not raw_body.strip():
+            # Hard-fail rather than stage an empty synthetic tool result.
+            # An empty `content` field silently tells the model "the article
+            # has nothing in it" and it confabulates from RAG/history. Better
+            # to surface a clean error to the user.
+            logger.warning(
+                "Article discussion aborted: empty body for rss_item %s (%s)",
+                item.id, item.url,
+            )
+            raise EmptyArticleError(
+                "Couldn't extract any readable text from this article."
+            )
         article_content = await prepare_article_context(
             item.title or "", item.url, raw_body, model,
         )
-        if article_content:
-            async with async_session() as session:
-                fresh = await session.get(RssItem, item.id)
-                if fresh is not None:
-                    fresh.context_prepared = article_content
-                    await session.commit()
+        if not article_content.strip():
+            raise EmptyArticleError(
+                "Couldn't extract any readable text from this article."
+            )
+        async with async_session() as session:
+            fresh = await session.get(RssItem, item.id)
+            if fresh is not None:
+                fresh.context_prepared = article_content
+                await session.commit()
 
     synthetic_tool_calls = [{
         "function": "read_article",
diff --git a/src/fabledassistant/services/llm.py b/src/fabledassistant/services/llm.py
index f88e833..ba7ab13 100644
--- a/src/fabledassistant/services/llm.py
+++ b/src/fabledassistant/services/llm.py
@@ -724,18 +724,27 @@ async def build_context(
     orphan_only = rag_project_id is None
     effective_project_id = rag_project_id if (rag_project_id is not None and rag_project_id != -1) else None
 
-    try:
-        from fabledassistant.services.embeddings import semantic_search_notes
-        for score, note in await semantic_search_notes(
-            user_id, user_message, exclude_ids=search_exclude or None, limit=8,
-            project_id=effective_project_id,
-            orphan_only=orphan_only,
-        ):
-            found_scored.append((score, note))
-    except Exception:
-        logger.warning("Semantic note search failed, falling back to keyword search", exc_info=True)
+    # Skip RAG auto-injection on the first turn of a seeded article discussion.
+    # The article body is already the sole context the user wants — pulling in
+    # unrelated orphan notes tricks the model into summarizing those instead.
+    # Follow-up turns keep RAG on because by then the user's own messages drive
+    # the query rather than the generic seed prompt.
+    from fabledassistant.services.article_context import ARTICLE_DISCUSS_SEED
+    _skip_rag_for_article_seed = user_message.strip() == ARTICLE_DISCUSS_SEED
 
-    if not found_scored:
+    if not _skip_rag_for_article_seed:
+        try:
+            from fabledassistant.services.embeddings import semantic_search_notes
+            for score, note in await semantic_search_notes(
+                user_id, user_message, exclude_ids=search_exclude or None, limit=8,
+                project_id=effective_project_id,
+                orphan_only=orphan_only,
+            ):
+                found_scored.append((score, note))
+        except Exception:
+            logger.warning("Semantic note search failed, falling back to keyword search", exc_info=True)
+
+    if not found_scored and not _skip_rag_for_article_seed:
         keywords = _extract_keywords(user_message)
         if keywords:
             try: