app/frontend/ui.py

@@ -5,6 +5,7 @@ import os
 import json
 import re
 import yaml
+import unicodedata
 from datetime import datetime
 from pathlib import Path
 from dotenv import load_dotenv
@@ -71,15 +72,24 @@ if "user_id" not in st.session_state: st.session_state.user_id = str(uuid.uuid4(
 
 # --- HELPER FUNCTIONS ---
 
+def slugify(value):
+    """Erzeugt saubere Dateinamen aus Titeln."""
+    value = str(value)
+    value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
+    value = re.sub(r'[^\w\s-]', '', value).strip().lower()
+    return re.sub(r'[-\s]+', '-', value)
+
 def normalize_meta_and_body(meta, body):
     """Sanitizer: Stellt sicher, dass nur erlaubte Felder im Frontmatter bleiben."""
     ALLOWED_KEYS = {"title", "type", "status", "tags", "id", "created", "updated", "aliases", "lang"}
     clean_meta = {}
     extra_content = []
     
+    # Title Normalization
     if "titel" in meta and "title" not in meta:
         meta["title"] = meta.pop("titel")
     
+    # Tag Normalization
     tag_candidates = ["tags", "emotionale_keywords", "keywords", "schluesselwoerter"]
     all_tags = []
     for key in tag_candidates:
@@ -99,7 +109,12 @@ def normalize_meta_and_body(meta, body):
                 extra_content.append(f"## {header}\n{val}\n")
 
     if all_tags:
-        clean_meta["tags"] = list(set(all_tags))
+        # Bereinige Tags von '#' und Duplikaten
+        clean_tags = []
+        for t in all_tags:
+            t_clean = str(t).replace("#", "").strip()
+            if t_clean: clean_tags.append(t_clean)
+        clean_meta["tags"] = list(set(clean_tags))
 
     if extra_content:
         new_section = "\n".join(extra_content)
@@ -110,7 +125,7 @@ def normalize_meta_and_body(meta, body):
     return clean_meta, final_body
 
 def parse_markdown_draft(full_text):
-    """Robustes Parsing + Sanitization."""
+    """Robustes Parsing + Sanitization (YAML + Fallbacks)."""
     clean_text = full_text
     
     # 1. Markdown Code-Blöcke entfernen
@@ -129,9 +144,7 @@ def parse_markdown_draft(full_text):
         yaml_str = parts[1]
         body_candidate = parts[2]
         
-        # --- FIX 1: Hashtag-Cleaner für YAML ---
-        # Entfernt #, wenn sie innerhalb von [] stehen, um YAML-Kommentare zu verhindern.
-        # Wir entfernen pauschal # im YAML-Block, da Tags dort keine brauchen.
+        # FIX 1: Hashtag-Cleaner für YAML (gegen Syntaxfehler)
         yaml_str_clean = yaml_str.replace("#", "")
         
         try:
@@ -141,23 +154,28 @@ def parse_markdown_draft(full_text):
                 body = body_candidate.strip()
         except Exception as e:
             print(f"YAML Parsing Warning: {e}")
-            # Fallback: Body retten, Meta leer lassen
             body = body_candidate.strip()
             
-    # --- FIX 2: Type/Status Swap Korrektur ---
-    # Wenn das LLM halluziniert hat: type='draft' -> Das ist eigentlich der Status.
+    # FIX 3: Titel-Fallback aus H1
+    if not meta.get("title"):
+        h1_match = re.search(r"^#\s+(.*)$", body, re.MULTILINE)
+        if h1_match:
+            meta["title"] = h1_match.group(1).strip()
+            
+    # FIX 4: Type/Status Swap Korrektur
     if meta.get("type") == "draft":
         meta["status"] = "draft"
-        # Wir raten einen besseren Typ oder setzen default
-        meta["type"] = "experience" # Da Interviews oft Experiences sind
+        meta["type"] = "experience" 
         
     return normalize_meta_and_body(meta, body)
 
 def build_markdown_doc(meta, body):
     """Baut das finale Dokument zusammen."""
+    # ID Generation
     if "id" not in meta or meta["id"] == "generated_on_save":
-        safe_title = re.sub(r'[^a-zA-Z0-9]', '-', meta.get('title', 'note')).lower()[:30]
-        meta["id"] = f"{datetime.now().strftime('%Y%m%d')}-{safe_title}-{uuid.uuid4().hex[:4]}"
+        # Nutze slugify für ID
+        clean_slug = slugify(meta.get('title', 'note'))[:40] or "note"
+        meta["id"] = f"{datetime.now().strftime('%Y%m%d')}-{clean_slug}"
     
     meta["updated"] = datetime.now().strftime("%Y-%m-%d")
     
@@ -206,7 +224,6 @@ def send_chat_message(message: str, top_k: int, explain: bool):
         return {"error": str(e)}
 
 def analyze_draft_text(text: str, n_type: str):
-    """Ruft den neuen Intelligence-Service (WP-11) auf."""
     try:
         response = requests.post(
             INGEST_ANALYZE_ENDPOINT,
@@ -219,7 +236,6 @@ def analyze_draft_text(text: str, n_type: str):
         return {"error": str(e)}
 
 def save_draft_to_vault(markdown_content: str, filename: str = None):
-    """Ruft den neuen Persistence-Service (WP-11) auf."""
     try:
         response = requests.post(
             INGEST_SAVE_ENDPOINT,
@@ -242,7 +258,7 @@ def submit_feedback(query_id, node_id, score, comment=None):
 def render_sidebar():
     with st.sidebar:
         st.title("🧠 mindnet")
-        st.caption("v2.4 | Async Intelligence")
+        st.caption("v2.4.2 | Robust UI")
         mode = st.radio("Modus", ["💬 Chat", "📝 Manueller Editor"], index=0)
         st.divider()
         st.subheader("⚙️ Settings")
@@ -257,7 +273,6 @@ def render_sidebar():
     return mode, top_k, explain
 
 def render_draft_editor(msg):
-    # Ensure ID Stability
     if "query_id" not in msg or not msg["query_id"]:
         msg["query_id"] = str(uuid.uuid4())
     
@@ -270,7 +285,7 @@ def render_draft_editor(msg):
     widget_body_key = f"{key_base}_widget_body" 
     data_body_key = f"{key_base}_data_body"
 
-    # --- 1. INIT STATE (Nur beim allerersten Laden der Message) ---
+    # --- 1. INIT STATE ---
     if f"{key_base}_init" not in st.session_state:
         meta, body = parse_markdown_draft(msg["content"])
         if "type" not in meta: meta["type"] = "default"
@@ -278,27 +293,24 @@ def render_draft_editor(msg):
         tags = meta.get("tags", [])
         meta["tags_str"] = ", ".join(tags) if isinstance(tags, list) else str(tags)
 
-        # Persistent Data (Source of Truth)
+        # Persistent Data
         st.session_state[data_meta_key] = meta
         st.session_state[data_sugg_key] = []
         st.session_state[data_body_key] = body.strip()
         
-        # WIDGET KEYS INITIALISIEREN (Resurrection Fix)
-        # Wir setzen die Werte direkt in den Widget-Key, damit Streamlit sie beim ersten Render findet.
+        # Widgets Init
         st.session_state[f"{key_base}_wdg_title"] = meta["title"]
         st.session_state[f"{key_base}_wdg_type"] = meta["type"]
         st.session_state[f"{key_base}_wdg_tags"] = meta["tags_str"]
         
         st.session_state[f"{key_base}_init"] = True
 
-    # --- 2. RESURRECTION FIX (Body) ---
-    # Wenn wir vom Manuellen Editor zurückkommen, ist das Widget weg, aber die Daten sind noch da.
+    # --- 2. RESURRECTION ---
     if widget_body_key not in st.session_state and data_body_key in st.session_state:
         st.session_state[widget_body_key] = st.session_state[data_body_key]
 
     # --- CALLBACKS ---
     def _sync_meta():
-        # Schreibt Widget-Werte zurück in den Meta-Store
         meta = st.session_state[data_meta_key]
         meta["title"] = st.session_state.get(f"{key_base}_wdg_title", "")
         meta["type"] = st.session_state.get(f"{key_base}_wdg_type", "default")
@@ -306,11 +318,9 @@ def render_draft_editor(msg):
         st.session_state[data_meta_key] = meta
 
     def _sync_body():
-        # Sync Widget -> Data (Source of Truth)
         st.session_state[data_body_key] = st.session_state[widget_body_key]
 
     def _insert_text(text_to_insert):
-        # Insert in Widget Key und Sync Data
         current = st.session_state.get(widget_body_key, "")
         new_text = f"{current}\n\n{text_to_insert}"
         st.session_state[widget_body_key] = new_text
@@ -326,26 +336,19 @@ def render_draft_editor(msg):
     st.markdown(f'<div class="draft-box">', unsafe_allow_html=True)
     st.markdown("### 📝 Entwurf bearbeiten")
     
-    # Metadata Form
     meta_ref = st.session_state[data_meta_key]
     c1, c2 = st.columns([2, 1])
     with c1:
-        # FIX: Keine 'value=' Angabe, da der Key schon existiert
         st.text_input("Titel", key=f"{key_base}_wdg_title", on_change=_sync_meta)
         
     with c2:
         known_types = ["concept", "project", "decision", "experience", "journal", "value", "goal", "principle", "risk", "belief"]
-        # Sicherstellen, dass der aktuelle Typ in der Liste ist
         curr_type = st.session_state.get(f"{key_base}_wdg_type", meta_ref["type"])
         if curr_type not in known_types: known_types.append(curr_type)
-        
-        # FIX: Keine 'index=' Angabe, da der Key schon existiert
         st.selectbox("Typ", known_types, key=f"{key_base}_wdg_type", on_change=_sync_meta)
 
-    # Tags
     st.text_input("Tags", key=f"{key_base}_wdg_tags", on_change=_sync_meta)
 
-    # Tabs
     tab_edit, tab_intel, tab_view = st.tabs(["✏️ Inhalt", "🧠 Intelligence", "👁️ Vorschau"])
     
     # --- TAB 1: EDITOR ---
@@ -365,7 +368,6 @@ def render_draft_editor(msg):
         if st.button("🔍 Analyse starten", key=f"{key_base}_analyze"):
             st.session_state[data_sugg_key] = []
             
-            # Lese vom Widget (aktuell) oder Data (Fallback)
             text_to_analyze = st.session_state.get(widget_body_key, st.session_state.get(data_body_key, ""))
             current_doc_type = st.session_state.get(f"{key_base}_wdg_type", "concept")
 
@@ -382,7 +384,6 @@ def render_draft_editor(msg):
                     else:
                         st.success(f"{len(suggestions)} Vorschläge gefunden.")
         
-        # Render List
         suggestions = st.session_state[data_sugg_key]
         if suggestions:
             current_text_state = st.session_state.get(widget_body_key, "")
@@ -414,11 +415,12 @@ def render_draft_editor(msg):
     final_meta = {
         "id": "generated_on_save",
         "type": st.session_state.get(f"{key_base}_wdg_type", "default"),
-        "title": st.session_state.get(f"{key_base}_wdg_title", "Untitled"),
+        # Title mit Fallback (Widget > Meta > Untitled)
+        "title": st.session_state.get(f"{key_base}_wdg_title", meta_ref.get("title", "Untitled")),
         "status": "draft",
         "tags": final_tags
     }
-    # Final Doc aus Data
+    
     final_body = st.session_state.get(widget_body_key, st.session_state[data_body_key])
     final_doc = build_markdown_doc(final_meta, final_body)
     
@@ -433,14 +435,9 @@ def render_draft_editor(msg):
     with b1:
         if st.button("💾 Speichern & Indizieren", type="primary", key=f"{key_base}_save"):
             with st.spinner("Speichere im Vault..."):
-#                safe_title = re.sub(r'[^a-zA-Z0-9]', '-', final_meta["title"]).lower()[:30] or "draft"
-# FIX: .get() verwenden, falls 'title' fehlt
                 raw_title = final_meta.get("title", "draft")
-                safe_title = re.sub(r'[^a-zA-Z0-9]', '-', raw_title).lower()[:30] or "draft"
-                
-                fname = f"{datetime.now().strftime('%Y%m%d')}-{safe_title}.md"
-                
-                result = save_draft_to_vault(final_doc, filename=fname)
+                # Slugify für saubere Dateinamen
+                safe_title = slugify(raw_title)[:40] or "draft"
                 fname = f"{datetime.now().strftime('%Y%m%d')}-{safe_title}.md"
                 
                 result = save_draft_to_vault(final_doc, filename=fname)
@@ -460,7 +457,6 @@ def render_chat_interface(top_k, explain):
     for idx, msg in enumerate(st.session_state.messages):
         with st.chat_message(msg["role"]):
             if msg["role"] == "assistant":
-                # Header
                 intent = msg.get("intent", "UNKNOWN")
                 src = msg.get("intent_source", "?")
                 icon = {"EMPATHY":"❤️", "DECISION":"⚖️", "CODING":"💻", "FACT":"📚", "INTERVIEW":"📝"}.get(intent, "🧠")
@@ -469,13 +465,11 @@ def render_chat_interface(top_k, explain):
                 with st.expander("🐞 Debug Raw Payload", expanded=False):
                     st.json(msg)
 
-                # Logic
                 if intent == "INTERVIEW":
                     render_draft_editor(msg)
                 else:
                     st.markdown(msg["content"])
                 
-                # Sources
                 if "sources" in msg and msg["sources"]:
                     for hit in msg["sources"]:
                         with st.expander(f"📄 {hit.get('note_id', '?')} ({hit.get('total_score', 0):.2f})"):