feat(briefing): cache + map-reduce article context for rich discuss chats

The Discuss button on news cards was producing one-shot replies because
the model got the whole trafilatura blob dropped into history with a
canned "summarize and discuss this article" prompt — no length guard, no
prep, no invitation to converse. Large articles got silently truncated by
Ollama; small articles got a tepid reply.

This reworks discuss_article around a three-layer cache:

  context_prepared  →  content_full  →  fresh trafilatura fetch

First click on a small article fetches once, writes through to both
caches, and passes the body straight into the synthetic read_article
tool-result. First click on a large article additionally runs a parallel
map step (services/article_context.py) that chunks the body on paragraph
boundaries, summarizes each ~8k chunk to ~300 words of dense factual
prose via the background model, and concatenates the summaries under
section headers — all pinned to num_ctx=16384 so the map step doesn't
itself fall victim to silent truncation. Repeat clicks on either path
skip straight to the chat turn.

The canned summary prompt is replaced with a conversational seed that
invites the user into an actual discussion rather than a one-shot
synopsis, matching the goal of "have a conversation about an article,
not just read it."

discuss_topic is intentionally left untouched — it's the multi-article
aggregation path and needs a separate rework. Follow-up task will decide
whether to retire it or rework it on the cached-context approach.

Closes task #106.

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

src/fabledassistant/routes/briefing.py

@@ -532,8 +532,28 @@ async def discuss_article(item_id: int):
     if get_buffer(conv_id) is not None:
         return jsonify({"error": "Generation already in progress"}), 409
 
-    from fabledassistant.services.rss import _fetch_full_article
-    article_content = await _fetch_full_article(item.url) or item.content or ""
+    # Three-layer cache: context_prepared (post-map-reduce) → content_full
+    # (raw trafilatura) → fresh fetch. Only the first miss pays the fetch
+    # cost; only a large uncached article pays the map-reduce cost. Repeat
+    # clicks on the same article skip straight to the chat turn.
+    from fabledassistant.services.article_context import prepare_article_context
+    from fabledassistant.services.rss import get_or_fetch_full_article
+
+    model = await get_setting(uid, "default_model", "") or ""
+
+    if item.context_prepared:
+        article_content = item.context_prepared
+    else:
+        raw_body = await get_or_fetch_full_article(item) or item.content or ""
+        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()
 
     # Store synthetic assistant message with read_article tool result
     synthetic_tool_calls = [{
@@ -549,8 +569,17 @@ async def discuss_article(item_id: int):
     }]
     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.")
+    # Conversational seed — invites a real discussion rather than asking for
+    # a one-shot summary. The model sees the article context in the tool
+    # result above and responds to this user turn as the start of an ongoing
+    # conversation the user will steer with follow-ups.
+    discuss_prompt = (
+        "I want to talk about this article. Start with a substantive summary "
+        "of what it's arguing and the key evidence it uses, then tell me what "
+        "stood out to you or seems worth pushing back on. I'll ask follow-ups "
+        "from there."
+    )
+    await add_message(conv_id, "user", discuss_prompt)
 
     # Reload conversation with fresh messages to build history
     conv = await get_conversation(uid, conv_id)
@@ -572,15 +601,13 @@ async def discuss_article(item_id: int):
         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.",
+        discuss_prompt,
     ))
 
     return jsonify({"assistant_message_id": assistant_msg.id, "status": "generating"}), 202