Add Tiptap inline-preview editor, layout improvements, and README

Replace plain textarea with Tiptap (ProseMirror) WYSIWYG editor for notes
and tasks. Headings, bold, lists, and code blocks now render inline while
editing. Tags and wikilinks get visual highlighting via decoration plugins,
and autocomplete uses @tiptap/suggestion with heading disambiguation.

Layout: pin navbar with app-shell flex column (100dvh), sticky editor
toolbar above scrolling content, AI Assist panel fixed at bottom 1/3 with
full-height section selector and prompt. Increase max-width to 960px
across all views. Hide assist controls during streaming/review.

Other fixes: markdown paste handling, auto-syncing assist sections via
body watcher, trailing newline on AI accept, ChatView height fix.

Add README.md describing the app, usage guide, and technical overview.
Update summary.md with Phase 5.2 roadmap and current status.

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

src/fabledassistant/routes/notes.py

@@ -1,8 +1,13 @@
+import json
+import logging
 from datetime import date
 
-from quart import Blueprint, jsonify, request
+from quart import Blueprint, Response, jsonify, request
 
 from fabledassistant.auth import login_required, get_current_user_id
+from fabledassistant.config import Config
+from fabledassistant.services.assist import build_assist_messages
+from fabledassistant.services.llm import stream_chat
 from fabledassistant.services.notes import (
     convert_note_to_task,
     convert_task_to_note,
@@ -16,8 +21,11 @@ from fabledassistant.services.notes import (
     list_notes,
     update_note,
 )
+from fabledassistant.services.settings import get_setting
 from fabledassistant.utils.tags import extract_tags
 
+logger = logging.getLogger(__name__)
+
 notes_bp = Blueprint("notes", __name__, url_prefix="/api/notes")
 
 
@@ -178,3 +186,41 @@ async def get_backlinks_route(note_id: int):
     uid = get_current_user_id()
     links = await get_backlinks(uid, note_id)
     return jsonify({"backlinks": links})
+
+
+@notes_bp.route("/assist", methods=["POST"])
+@login_required
+async def assist_route():
+    """Stream an AI-assisted section edit via SSE."""
+    uid = get_current_user_id()
+    data = await request.get_json()
+
+    body = data.get("body", "")
+    target_section = data.get("target_section", "")
+    instruction = data.get("instruction", "")
+
+    if not target_section or not instruction:
+        return jsonify({"error": "target_section and instruction are required"}), 400
+
+    model = await get_setting(uid, "default_model", Config.OLLAMA_MODEL)
+    messages = build_assist_messages(body, target_section, instruction)
+
+    async def generate():
+        full_text = ""
+        try:
+            async for chunk in stream_chat(messages, model):
+                full_text += chunk
+                yield f"data: {json.dumps({'chunk': chunk})}\n\n"
+            yield f"data: {json.dumps({'done': True, 'full_text': full_text})}\n\n"
+        except Exception as e:
+            logger.exception("Assist generation failed")
+            yield f"data: {json.dumps({'error': str(e)})}\n\n"
+
+    return Response(
+        generate(),
+        content_type="text/event-stream",
+        headers={
+            "Cache-Control": "no-cache",
+            "X-Accel-Buffering": "no",
+        },
+    )

src/fabledassistant/services/assist.py

@@ -0,0 +1,35 @@
+MAX_BODY_CHARS = 3000
+
+
+def build_assist_messages(
+    body: str, target_section: str, instruction: str
+) -> list[dict]:
+    """Build Ollama messages for section-level assist.
+
+    The full note body (truncated) is provided as read-only context in the
+    system prompt.  The target section + user instruction go in the user
+    message.  The model outputs only the replacement for the target section.
+    """
+    truncated_body = body[:MAX_BODY_CHARS]
+    if len(body) > MAX_BODY_CHARS:
+        truncated_body += "\n... (truncated)"
+
+    system_content = (
+        "You are an AI writing assistant integrated into a note-taking app. "
+        "The user is editing a document. The full document is shown below for context.\n\n"
+        f"--- Full Document ---\n{truncated_body}\n--- End Document ---\n\n"
+        "The user will give you a specific section of the document and an instruction. "
+        "Output ONLY the replacement text for that section. "
+        "Do not include other sections, explanatory text, or markdown code fences around the output. "
+        "Match the document's existing tone and style."
+    )
+
+    user_content = (
+        f"--- Target Section ---\n{target_section}\n--- End Target Section ---\n\n"
+        f"Instruction: {instruction}"
+    )
+
+    return [
+        {"role": "system", "content": system_content},
+        {"role": "user", "content": user_content},
+    ]

src/fabledassistant/services/chat.py

@@ -6,8 +6,10 @@ from sqlalchemy.orm import selectinload
 
 from fabledassistant.models import async_session
 from fabledassistant.models.conversation import Conversation, Message
+from fabledassistant.config import Config
 from fabledassistant.services.llm import generate_completion
 from fabledassistant.services.notes import create_note
+from fabledassistant.services.settings import get_setting
 
 logger = logging.getLogger(__name__)
 
@@ -166,7 +168,9 @@ async def save_response_as_note(user_id: int, message_id: int) -> dict:
     # Generate title via LLM using the assistant message content
     title = ""
     if conv:
-        model = conv.model or "llama3.2"
+        model = conv.model or await get_setting(
+            user_id, "default_model", Config.OLLAMA_MODEL
+        )
         try:
             prompt_messages = [
                 {