feat(briefing): add article Discuss endpoint with synthetic tool exchange

POST /api/briefing/articles/<id>/discuss injects stored article content
as a persisted read_article tool exchange before triggering generation.
The LLM sees the article as already read; follow-ups retain context via
the fixed history builder. Frontend Discuss button now calls the new
endpoint instead of inlining article text in the user message.

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

frontend/src/views/BriefingView.vue

@@ -7,6 +7,7 @@ import WeatherCard from '@/components/WeatherCard.vue'
 import BriefingSetupWizard from '@/components/BriefingSetupWizard.vue'
 import {
   apiGet,
+  apiPost,
   getBriefingConfig,
   getBriefingConversations,
   getBriefingToday,
@@ -113,26 +114,19 @@ watch(selectedConvId, async (id) => {
   }
 })
 
-// Keep send() as a helper for discussArticle
-async function send(text: string) {
-  if (!text || !todayConvId.value || chatStore.streaming) return
-  if (chatStore.currentConversation?.id !== todayConvId.value) {
-    await chatStore.fetchConversation(todayConvId.value)
-  }
-  await chatStore.sendMessage(text, undefined, undefined, true)
-}
-
 async function discussArticle(item: NewsItem) {
-  if (!todayConvId.value) return
+  if (!todayConvId.value || chatStore.streaming) return
   if (!isToday.value) selectedConvId.value = todayConvId.value
-  const body = (item.content || item.snippet || '').trim()
-  const bodyBlock = body ? `\n\n---\n${body}\n---` : ''
-  const text = `Please summarize and share your thoughts on this article. Do not use any research or search tools — respond conversationally based only on the content below.\n\n**${item.title}**\nSource: ${item.source}${bodyBlock}`
-  // Scroll to chat column
   await nextTick(() => {
     document.querySelector('.briefing-center')?.scrollIntoView({ behavior: 'smooth', block: 'nearest' })
   })
-  await send(text)
+  try {
+    await apiPost<{ assistant_message_id: number }>(`/api/briefing/articles/${item.id}/discuss`, { conv_id: todayConvId.value })
+  } catch {
+    return
+  }
+  await chatStore.fetchConversation(todayConvId.value)
+  await chatStore.reconnectIfGenerating(todayConvId.value)
 }
 
 // RSS reactions: map of rss_item_id -> 'up' | 'down' | null

src/fabledassistant/routes/briefing.py

@@ -10,7 +10,7 @@ from sqlalchemy import select
 from fabledassistant.auth import login_required
 from fabledassistant.models import async_session
 from fabledassistant.models.conversation import Conversation, Message
-from fabledassistant.models.rss_feed import RssFeed
+from fabledassistant.models.rss_feed import RssFeed, RssItem
 from fabledassistant.services import rss as rss_svc
 from fabledassistant.services import weather as weather_svc
 from fabledassistant.services.briefing_conversations import (
@@ -18,6 +18,9 @@ from fabledassistant.services.briefing_conversations import (
     list_briefing_conversations,
     post_message,
 )
+from fabledassistant.services.chat import add_message, get_conversation
+from fabledassistant.services.generation_buffer import create_buffer, get_buffer
+from fabledassistant.services.generation_task import run_generation
 from fabledassistant.services.settings import get_setting, set_settings_batch
 
 logger = logging.getLogger(__name__)
@@ -415,3 +418,90 @@ async def list_news():
         for r in rows
     ]
     return jsonify({"items": items, "offset": offset, "limit": limit})
+
+
+# ── Article Discuss ────────────────────────────────────────────────────────────
+
+@briefing_bp.route("/articles/<int:item_id>/discuss", methods=["POST"])
+@_REQUIRE
+async def discuss_article(item_id: int):
+    """Inject article content as a synthetic tool exchange and trigger generation."""
+    data = await request.get_json() or {}
+    conv_id = data.get("conv_id")
+    if not conv_id:
+        return jsonify({"error": "conv_id required"}), 400
+
+    uid = g.user.id
+
+    # Verify item belongs to user via feed ownership
+    async with async_session() as session:
+        result = await session.execute(
+            select(RssItem)
+            .join(RssFeed, RssFeed.id == RssItem.feed_id)
+            .where(RssItem.id == item_id, RssFeed.user_id == uid)
+        )
+        item = result.scalars().first()
+    if item is None:
+        return jsonify({"error": "Not found"}), 404
+
+    # Verify conversation belongs to user
+    conv = await get_conversation(uid, conv_id)
+    if conv is None:
+        return jsonify({"error": "Conversation not found"}), 404
+
+    # Reject if generation already running
+    if get_buffer(conv_id) is not None:
+        return jsonify({"error": "Generation already in progress"}), 409
+
+    article_content = item.content or ""
+
+    # Store synthetic assistant message with read_article tool result
+    synthetic_tool_calls = [{
+        "function": "read_article",
+        "arguments": {"url": item.url},
+        "result": {
+            "success": True,
+            "type": "article_content",
+            "url": item.url,
+            "content": article_content,
+            "truncated": False,
+        },
+    }]
+    await add_message(conv_id, "assistant", "", status="complete", tool_calls=synthetic_tool_calls)
+
+    # Store user message
+    await add_message(conv_id, "user", "Please summarize and discuss this article.")
+
+    # Reload conversation with fresh messages to build history
+    conv = await get_conversation(uid, conv_id)
+    assert conv is not None
+
+    history = []
+    for msg in conv.messages:
+        if msg.role == "system":
+            continue
+        msg_dict = {"role": msg.role, "content": msg.content or ""}
+        if msg.tool_calls:
+            msg_dict["tool_calls"] = [
+                {"function": {"name": tc["function"], "arguments": tc["arguments"]}}
+                for tc in msg.tool_calls
+            ]
+            history.append(msg_dict)
+            for tc in msg.tool_calls:
+                history.append({"role": "tool", "content": json.dumps(tc.get("result", {}))})
+        else:
+            history.append(msg_dict)
+
+    model = await get_setting(uid, "default_model", "") or ""
+
+    assistant_msg = await add_message(conv_id, "assistant", "", status="generating")
+    buf = create_buffer(conv_id, assistant_msg.id)
+
+    asyncio.create_task(run_generation(
+        buf, history, model,
+        uid, conv_id, conv.title or "",
+        "Please summarize and discuss this article.",
+        think=True,
+    ))
+
+    return jsonify({"assistant_message_id": assistant_msg.id, "status": "generating"}), 202