diff --git a/app/frontend/ui.py b/app/frontend/ui.py index ee7051f..3d8e65e 100644 --- a/app/frontend/ui.py +++ b/app/frontend/ui.py @@ -1,9 +1,3 @@ -# app/frontend/ui.py - -# ... (Imports und Setup bleiben gleich) ... - -# Ersetze die gesamte Datei mit diesem Inhalt: - import streamlit as st import requests import uuid @@ -30,7 +24,7 @@ timeout_setting = os.getenv("MINDNET_API_TIMEOUT") or os.getenv("MINDNET_LLM_TIM API_TIMEOUT = float(timeout_setting) if timeout_setting else 300.0 # --- PAGE SETUP --- -st.set_page_config(page_title="mindnet v2.4", page_icon="🧠", layout="wide") +st.set_page_config(page_title="mindnet v2.5", page_icon="🧠", layout="wide") # --- CSS STYLING --- st.markdown(""" @@ -70,10 +64,6 @@ if "user_id" not in st.session_state: st.session_state.user_id = str(uuid.uuid4( # --- HELPER FUNCTIONS --- def slugify(value): - """ - Erzeugt saubere Dateinamen (German-Aware). - z.B. "Müller & Söhne" -> "mueller-und-soehne" - """ if not value: return "" value = str(value).lower() replacements = {'ä': 'ae', 'ö': 'oe', 'ü': 'ue', 'ß': 'ss', '&': 'und', '+': 'und'} @@ -85,7 +75,6 @@ def slugify(value): 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 = [] @@ -127,37 +116,49 @@ def normalize_meta_and_body(meta, body): return clean_meta, final_body def parse_markdown_draft(full_text): - """Robustes Parsing + Sanitization (YAML + Fallbacks).""" + """ + HEALING PARSER: Repariert kaputten LLM Output (z.B. fehlendes schließendes '---'). + """ clean_text = full_text.strip() - # 1. Markdown Code-Blöcke entfernen + # 1. Code-Block Wrapper entfernen pattern_block = r"```(?:markdown|md|yaml)?\s*(.*?)\s*```" match_block = re.search(pattern_block, clean_text, re.DOTALL | re.IGNORECASE) if match_block: clean_text = match_block.group(1).strip() - # 2. Split YAML / Body - parts = re.split(r"^---+\s*$", clean_text, maxsplit=2, flags=re.MULTILINE) - meta = {} body = clean_text + yaml_str = "" + # 2. Versuch A: Standard Split (Idealfall) + parts = re.split(r"^---+\s*$", clean_text, maxsplit=2, flags=re.MULTILINE) + if len(parts) >= 3: yaml_str = parts[1] - body_candidate = parts[2] - - # YAML Cleanup - yaml_str_clean = yaml_str.replace("#", "") + body = parts[2] + + # 3. Versuch B: Healing (Wenn LLM das schließende --- vergessen hat) + elif clean_text.startswith("---"): + # Wir suchen die erste Überschrift '#', da Frontmatter davor sein muss + # Pattern: Suche --- am Anfang, dann nimm alles bis zum ersten # am Zeilenanfang + fallback_match = re.search(r"^---\s*(.*?)(?=\n#)", clean_text, re.DOTALL | re.MULTILINE) + if fallback_match: + yaml_str = fallback_match.group(1) + # Der Body ist alles NACH dem YAML String (inklusive dem #) + body = clean_text.replace(f"---{yaml_str}", "", 1).strip() + + # 4. YAML Parsing + if yaml_str: + yaml_str_clean = yaml_str.replace("#", "") # Tags cleanen try: parsed = yaml.safe_load(yaml_str_clean) if isinstance(parsed, dict): meta = parsed - body = body_candidate.strip() except Exception as e: print(f"YAML Parsing Warning: {e}") - body = body_candidate.strip() - - # Fallback: Titel aus H1 suchen, wenn nicht im YAML + + # Fallback: Titel aus H1 if not meta.get("title"): h1_match = re.search(r"^#\s+(.*)$", body, re.MULTILINE) if h1_match: @@ -258,7 +259,7 @@ def submit_feedback(query_id, node_id, score, comment=None): def render_sidebar(): with st.sidebar: st.title("🧠 mindnet") - st.caption("v2.4.4 | Smart Filename") + st.caption("v2.5 | Healing Parser") mode = st.radio("Modus", ["💬 Chat", "📝 Manueller Editor"], index=0) st.divider() st.subheader("⚙️ Settings") @@ -289,7 +290,7 @@ def render_draft_editor(msg): if f"{key_base}_init" not in st.session_state: meta, body = parse_markdown_draft(msg["content"]) if "type" not in meta: meta["type"] = "default" - if "title" not in meta: meta["title"] = "" # Kann leer sein + if "title" not in meta: meta["title"] = "" tags = meta.get("tags", []) meta["tags_str"] = ", ".join(tags) if isinstance(tags, list) else str(tags) @@ -412,7 +413,6 @@ def render_draft_editor(msg): final_tags_str = st.session_state.get(f"{key_base}_wdg_tags", "") final_tags = [t.strip() for t in final_tags_str.split(",") if t.strip()] - # Live Daten aus Widget (dies ist die Wahrheit!) final_meta = { "id": "generated_on_save", "type": st.session_state.get(f"{key_base}_wdg_type", "default"), @@ -423,14 +423,11 @@ def render_draft_editor(msg): final_body = st.session_state.get(widget_body_key, st.session_state[data_body_key]) - # 1. Update Title in Meta (damit es im YAML landet) if not final_meta["title"]: - # Fallback auf H1 im Text h1_match = re.search(r"^#\s+(.*)$", final_body, re.MULTILINE) if h1_match: final_meta["title"] = h1_match.group(1).strip() - # 2. Build Doc final_doc = build_markdown_doc(final_meta, final_body) with tab_view: @@ -445,20 +442,13 @@ def render_draft_editor(msg): if st.button("💾 Speichern & Indizieren", type="primary", key=f"{key_base}_save"): with st.spinner("Speichere im Vault..."): - # --- DATEINAMEN INTELLIGENZ --- - # Prio 1: Meta Titel - title_for_slug = final_meta.get("title", "") - - # Prio 2: Body Snippet (wenn Titel immer noch leer) - if not title_for_slug: + raw_title = final_meta.get("title", "") + if not raw_title: clean_body = re.sub(r"[#*_\[\]()]", "", final_body).strip() - title_for_slug = clean_body[:40] if clean_body else "draft" - - safe_title = slugify(title_for_slug)[:60] - if not safe_title: safe_title = "draft" + raw_title = clean_body[:40] if clean_body else "draft" + safe_title = slugify(raw_title)[:60] or "draft" fname = f"{datetime.now().strftime('%Y%m%d')}-{safe_title}.md" - # ----------------------------- result = save_draft_to_vault(final_doc, filename=fname) if "error" in result: diff --git a/app/services/llm_service.py b/app/services/llm_service.py index 0565b87..bfbe343 100644 --- a/app/services/llm_service.py +++ b/app/services/llm_service.py @@ -1,6 +1,6 @@ """ app/services/llm_service.py — LLM Client -Version: 2.7.0 (Clean Architecture: Explicit Priority Queues) +Version: 2.8.0 (Configurable Concurrency Limit) """ import httpx @@ -19,17 +19,28 @@ class Settings: LLM_MODEL = os.getenv("MINDNET_LLM_MODEL", "phi3:mini") PROMPTS_PATH = os.getenv("MINDNET_PROMPTS_PATH", "./config/prompts.yaml") + # NEU: Konfigurierbares Limit für Hintergrund-Last + # Default auf 2 (konservativ), kann in .env erhöht werden. + BACKGROUND_LIMIT = int(os.getenv("MINDNET_LLM_BACKGROUND_LIMIT", "2")) + def get_settings(): return Settings() class LLMService: - # GLOBALER SEMAPHOR (Drosselung für Hintergrund-Prozesse) - _background_semaphore = asyncio.Semaphore(2) + # GLOBALER SEMAPHOR (Lazy Initialization) + # Wir initialisieren ihn erst, wenn wir die Settings kennen. + _background_semaphore = None def __init__(self): self.settings = get_settings() self.prompts = self._load_prompts() + # Initialisiere Semaphore einmalig auf Klassen-Ebene basierend auf Config + if LLMService._background_semaphore is None: + limit = self.settings.BACKGROUND_LIMIT + logger.info(f"🚦 LLMService: Initializing Background Semaphore with limit: {limit}") + LLMService._background_semaphore = asyncio.Semaphore(limit) + self.timeout = httpx.Timeout(self.settings.LLM_TIMEOUT, connect=10.0) self.client = httpx.AsyncClient( @@ -53,7 +64,7 @@ class LLMService: force_json: bool = False, max_retries: int = 0, base_delay: float = 2.0, - priority: Literal["realtime", "background"] = "realtime" # <--- NEU & EXPLIZIT + priority: Literal["realtime", "background"] = "realtime" ) -> str: """ Führt einen LLM Call aus. @@ -61,13 +72,13 @@ class LLMService: priority="background": Import/Analyse (Gedrosselt durch Semaphore). """ - # Entscheidung basierend auf explizitem Parameter, nicht Format! use_semaphore = (priority == "background") - if use_semaphore: + if use_semaphore and LLMService._background_semaphore: async with LLMService._background_semaphore: return await self._execute_request(prompt, system, force_json, max_retries, base_delay) else: + # Realtime oder Fallback (falls Semaphore Init fehlschlug) return await self._execute_request(prompt, system, force_json, max_retries, base_delay) async def _execute_request(self, prompt, system, force_json, max_retries, base_delay): @@ -123,7 +134,7 @@ class LLMService: system=system_prompt, max_retries=0, force_json=False, - priority="realtime" # <--- Standard + priority="realtime" ) async def close(self):