Implement RAG summarization and context pipeline

- Add ContextPipeline for async RAG lookups
- Implement RAG result summarization via LLMProcessor
- Add CLI flag for PDF ingestion
- Strip markdown code blocks from LLM responses
- Update TUI context display to use ListItems

src/ui/tui.py

@@ -3,7 +3,16 @@ from typing import List, Optional, Union
 
 from textual.app import App, ComposeResult
 from textual.containers import Container, Horizontal, Vertical
-from textual.widgets import Button, DataTable, Footer, Input, Label, ListView, Static
+from textual.widgets import (
+    Button,
+    DataTable,
+    Footer,
+    Input,
+    Label,
+    ListItem,
+    ListView,
+    Static,
+)
 
 from src.llm.models import CharacterStateUpdate, ExtractionResult, LoreUpdate
 from src.persistence.characters import update_character_state
@@ -181,8 +190,8 @@ class ConfirmationApp(App):
                 # Format the update for display
                 display_text = f"Query: {update.query}\nSource: {update.source}\n\n{update.snippet}"
 
-                # Add a new Static widget to the ListView
-                context_pane.mount(Static(display_text))
+                # Add a new ListItem widget to the top of the ListView for 'most recent'
+                context_pane.mount(ListItem(Label(display_text), index=0))
 
                 if hasattr(self.context_queue, "task_done"):
                     self.context_queue.task_done()