feat(fable-mcp): briefing introspection and manual trigger tools

Adds the MCP tools needed to debug the agentic briefing pipeline
without waiting for scheduled slots to fire:

- fable_list_briefings — list briefing conversations newest first
- fable_get_today_briefing — fetch today's briefing with all messages
- fable_get_briefing_messages(conv_id) — message list for a specific
  briefing conversation, including tool_calls with embedded results
- fable_trigger_briefing(slot) — manually run a slot via
  POST /api/briefing/trigger (fires RSS/weather refresh, same as
  the scheduler)
- fable_get_conversation(conv_id) — generic conversation read for
  chat or briefing threads, full messages + tool_calls + metadata

All of these hit existing REST endpoints (/api/briefing/conversations,
/api/briefing/conversations/<id>/messages, /api/briefing/trigger,
/api/chat/conversations/<id>) so no API surface changed — the gap
was purely on the MCP side. Bearer token auth works across both
blueprints because login_required already accepts API keys.

Enables a full "trigger → inspect → tune prompt → repeat" loop from
Claude without touching the UI, which is necessary for iterating on
agentic briefing prompts when the scheduled slot is hours away.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

fable-mcp/fable_mcp/server.py

@@ -628,6 +628,100 @@ async def fable_remove_rss_feed(feed_id: int) -> dict:
         return await briefing.remove_rss_feed(client, feed_id=feed_id)
 
 
+# ---------------------------------------------------------------------------
+# Briefing introspection & control
+# ---------------------------------------------------------------------------
+
+
+@mcp.tool()
+async def fable_list_briefings() -> dict:
+    """List the user's briefing conversations, newest first.
+
+    Each briefing has an associated date and conversation id. Use
+    ``fable_get_briefing_messages`` or ``fable_get_conversation`` with
+    the id to pull the actual briefing text and tool-call receipts.
+
+    Returns a dict with a ``conversations`` list.
+    """
+    async with FableClient() as client:
+        return await briefing.list_briefing_conversations(client)
+
+
+@mcp.tool()
+async def fable_get_today_briefing() -> dict:
+    """Fetch today's briefing conversation, creating it if needed.
+
+    Returns the full conversation object including all messages — the
+    scheduled briefing assistant turns, any tool calls the agentic path
+    made, and any chat replies the user has sent in the briefing thread.
+
+    Use this to inspect what a briefing actually said (and what tool
+    results grounded it) without having to query by id.
+    """
+    async with FableClient() as client:
+        return await briefing.get_today_briefing(client)
+
+
+@mcp.tool()
+async def fable_get_briefing_messages(conversation_id: int) -> dict:
+    """Fetch all messages for a specific briefing conversation.
+
+    Args:
+        conversation_id: The briefing conversation id from fable_list_briefings.
+
+    Returns a dict with a ``messages`` list. Each message includes
+    role, content, tool_calls (with results), and metadata — the
+    metadata carries ``briefing_slot`` tags on agentic briefing turns.
+    """
+    async with FableClient() as client:
+        return await briefing.get_briefing_messages(
+            client, conversation_id=conversation_id,
+        )
+
+
+@mcp.tool()
+async def fable_trigger_briefing(slot: str = "compilation") -> dict:
+    """Manually run a briefing slot for the current user.
+
+    Fires the same data refresh the scheduler does (RSS, weather),
+    runs the briefing pipeline (legacy or agentic based on the user's
+    ``briefing_mode`` setting), and writes the result into today's
+    briefing conversation. Use this to test prompt changes without
+    waiting for the next scheduled slot.
+
+    Args:
+        slot: One of ``compilation`` (full morning, default), ``morning``,
+              ``midday``, or ``afternoon``.
+
+    Returns a dict with ``conversation_id``, ``message_id``, and ``slot``.
+    """
+    async with FableClient() as client:
+        return await briefing.trigger_briefing(client, slot=slot)
+
+
+# ---------------------------------------------------------------------------
+# Generic conversation access
+# ---------------------------------------------------------------------------
+
+
+@mcp.tool()
+async def fable_get_conversation(conversation_id: int) -> dict:
+    """Fetch any conversation (chat or briefing) with its full message list.
+
+    Returns conversation metadata plus an ordered ``messages`` array.
+    Each message includes role, content, tool_calls (with results),
+    context_note_id, and msg_metadata. Tool calls are in the stored
+    flat format: ``[{"function": name, "arguments": {...}, "result": {...}}]``.
+
+    Useful for debugging agentic briefings, inspecting chat history,
+    or verifying that a tool actually ran with the expected arguments.
+    """
+    async with FableClient() as client:
+        return await briefing.get_conversation(
+            client, conversation_id=conversation_id,
+        )
+
+
 # ---------------------------------------------------------------------------
 # Entry point
 # ---------------------------------------------------------------------------