""" FILE: app/core/ingestion/ingestion_processor.py DESCRIPTION: Der zentrale IngestionService (Orchestrator). WP-24c: Integration der Symmetrie-Logik (Automatische inverse Kanten). WP-25a: Integration der Mixture of Experts (MoE) Architektur. WP-15b: Two-Pass Workflow mit globalem Kontext-Cache. WP-20/22: Cloud-Resilienz und Content-Lifecycle integriert. AUDIT v3.1.8: Fix für HTTP 400 (Bad Request) durch ID-Validierung und Schutz vor System-Typ Kollisionen. VERSION: 3.1.8 (WP-24c: Robust Symmetry & ID Validation) STATUS: Active """ import logging import asyncio import os import re from typing import Dict, List, Optional, Tuple, Any # Core Module Imports from app.core.parser import ( read_markdown, pre_scan_markdown, normalize_frontmatter, validate_required_frontmatter, NoteContext ) from app.core.chunking import assemble_chunks # WP-24c: Import für die deterministische ID-Vorabberechnung from app.core.graph.graph_utils import _mk_edge_id # MODULARISIERUNG: Neue Import-Pfade für die Datenbank-Ebene from app.core.database.qdrant import QdrantConfig, get_client, ensure_collections, ensure_payload_indexes from app.core.database.qdrant_points import points_for_chunks, points_for_note, points_for_edges, upsert_batch from qdrant_client.http import models as rest # Services from app.services.embeddings_client import EmbeddingsClient from app.services.edge_registry import registry as edge_registry from app.services.llm_service import LLMService # Package-Interne Imports from .ingestion_utils import load_type_registry, resolve_note_type, get_chunk_config_by_profile from .ingestion_db import fetch_note_payload, artifacts_missing, purge_artifacts, is_explicit_edge_present from .ingestion_validation import validate_edge_candidate from .ingestion_note_payload import make_note_payload from .ingestion_chunk_payload import make_chunk_payloads # Fallback für Edges (Struktur-Verknüpfung) try: from app.core.graph.graph_derive_edges import build_edges_for_note except ImportError: def build_edges_for_note(*args, **kwargs): return [] logger = logging.getLogger(__name__) class IngestionService: def __init__(self, collection_prefix: str = None): """Initialisiert den Service und nutzt die neue database-Infrastruktur.""" from app.config import get_settings self.settings = get_settings() self.prefix = collection_prefix or self.settings.COLLECTION_PREFIX self.cfg = QdrantConfig.from_env() # Synchronisierung der Konfiguration mit dem Instanz-Präfix self.cfg.prefix = self.prefix self.client = get_client(self.cfg) self.registry = load_type_registry() self.embedder = EmbeddingsClient() self.llm = LLMService() # WP-25a: Auflösung der Dimension über das Embedding-Profil (MoE) embed_cfg = self.llm.profiles.get("embedding_expert", {}) self.dim = embed_cfg.get("dimensions") or self.settings.VECTOR_SIZE # Festlegen, welcher Hash für die Change-Detection maßgeblich ist self.active_hash_mode = self.settings.CHANGE_DETECTION_MODE self.batch_cache: Dict[str, NoteContext] = {} # WP-15b LocalBatchCache # WP-24c: Laufzeit-Speicher für explizite Kanten-IDs im aktuellen Batch self.processed_explicit_ids = set() try: # Aufruf der modularisierten Schema-Logik ensure_collections(self.client, self.prefix, self.dim) ensure_payload_indexes(self.client, self.prefix) except Exception as e: logger.warning(f"DB initialization warning: {e}") def _is_valid_note_id(self, text: str) -> bool: """ Prüft, ob ein String eine plausible Note-ID oder ein gültiger Titel ist. Verhindert Symmetrie-Kanten zu Typ-Strings wie 'insight', 'event' oder 'source'. """ if not text or len(text.strip()) < 3: return False # 1. Bekannte System-Typen oder Meta-Daten Begriffe ausschließen # Diese landen oft durch fehlerhafte Frontmatter-Einträge in der Referenz-Liste blacklisted = { "insight", "event", "source", "task", "project", "person", "concept", "value", "principle", "trip", "lesson", "decision", "requirement", "related_to" } clean_text = text.lower().strip() if clean_text in blacklisted: return False # 2. Ausschluss von zu langen Textfragmenten (wahrscheinlich kein Titel/ID) if len(text) > 120: return False return True async def run_batch(self, file_paths: List[str], vault_root: str) -> List[Dict[str, Any]]: """ WP-15b: Implementiert den Two-Pass Ingestion Workflow. Pass 1: Pre-Scan füllt den Context-Cache. Pass 2: Verarbeitung nutzt den Cache für die semantische Prüfung. """ # Reset der Authority-Registry für den neuen Batch self.processed_explicit_ids.clear() logger.info(f"🔍 [Pass 1] Pre-Scanning {len(file_paths)} files for Context Cache...") for path in file_paths: try: # Übergabe der Registry für dynamische Scan-Tiefe ctx = pre_scan_markdown(path, registry=self.registry) if ctx: # Mehrfache Indizierung für robusten Look-up (ID, Titel, Dateiname) self.batch_cache[ctx.note_id] = ctx self.batch_cache[ctx.title] = ctx fname = os.path.splitext(os.path.basename(path))[0] self.batch_cache[fname] = ctx except Exception as e: logger.warning(f"⚠️ Pre-scan failed for {path}: {e}") logger.info(f"🚀 [Pass 2] Semantic Processing of {len(file_paths)} files...") return [await self.process_file(p, vault_root, apply=True, purge_before=True) for p in file_paths] async def process_file(self, file_path: str, vault_root: str, **kwargs) -> Dict[str, Any]: """Transformiert eine Markdown-Datei in den Graphen.""" apply = kwargs.get("apply", False) force_replace = kwargs.get("force_replace", False) purge_before = kwargs.get("purge_before", False) note_scope_refs = kwargs.get("note_scope_refs", False) hash_source = kwargs.get("hash_source", "parsed") hash_normalize = kwargs.get("hash_normalize", "canonical") result = {"path": file_path, "status": "skipped", "changed": False, "error": None} # 1. Parse & Lifecycle Gate try: parsed = read_markdown(file_path) if not parsed: return {**result, "error": "Empty file"} fm = normalize_frontmatter(parsed.frontmatter) validate_required_frontmatter(fm) except Exception as e: return {**result, "error": f"Validation failed: {str(e)}"} # Dynamischer Lifecycle-Filter ingest_cfg = self.registry.get("ingestion_settings", {}) ignore_list = ingest_cfg.get("ignore_statuses", ["system", "template", "archive", "hidden"]) current_status = fm.get("status", "draft").lower().strip() if current_status in ignore_list: return {**result, "status": "skipped", "reason": "lifecycle_filter"} # 2. Payload & Change Detection note_type = resolve_note_type(self.registry, fm.get("type")) note_pl = make_note_payload( parsed, vault_root=vault_root, file_path=file_path, hash_source=hash_source, hash_normalize=hash_normalize, types_cfg=self.registry ) note_id = note_pl["note_id"] # Abgleich mit der Datenbank old_payload = None if force_replace else fetch_note_payload(self.client, self.prefix, note_id) # Prüfung gegen den konfigurierten Hash-Modus check_key = f"{self.active_hash_mode}:{hash_source}:{hash_normalize}" old_hash = (old_payload or {}).get("hashes", {}).get(check_key) new_hash = note_pl.get("hashes", {}).get(check_key) c_miss, e_miss = artifacts_missing(self.client, self.prefix, note_id) if not (force_replace or not old_payload or old_hash != new_hash or c_miss or e_miss): return {**result, "status": "unchanged", "note_id": note_id} if not apply: return {**result, "status": "dry-run", "changed": True, "note_id": note_id} # 3. Deep Processing try: body_text = getattr(parsed, "body", "") or "" edge_registry.ensure_latest() profile = note_pl.get("chunk_profile", "sliding_standard") chunk_cfg = get_chunk_config_by_profile(self.registry, profile, note_type) enable_smart = chunk_cfg.get("enable_smart_edge_allocation", False) chunks = await assemble_chunks(note_id, body_text, note_type, config=chunk_cfg) # Semantische Kanten-Validierung for ch in chunks: new_pool = [] for cand in getattr(ch, "candidate_pool", []): if cand.get("provenance") == "global_pool" and enable_smart: is_valid = await validate_edge_candidate( ch.text, cand, self.batch_cache, self.llm, profile_name="ingest_validator" ) if is_valid: new_pool.append(cand) else: new_pool.append(cand) ch.candidate_pool = new_pool chunk_pls = make_chunk_payloads( fm, note_pl["path"], chunks, file_path=file_path, types_cfg=self.registry ) vecs = await self.embedder.embed_documents([c.get("window") or "" for c in chunk_pls]) if chunk_pls else [] # Aggregation aller Kanten raw_edges = build_edges_for_note( note_id, chunk_pls, note_level_references=note_pl.get("references", []), include_note_scope_refs=note_scope_refs ) # --- WP-24c: Symmetrie-Injektion (Authority Implementation) --- final_edges = [] # PHASE 1: Alle expliziten Kanten vorverarbeiten und registrieren for e in raw_edges: target_raw = e.get("target_id") # Robustheits-Check: Ist das Ziel eine valide Note-ID? if not self._is_valid_note_id(target_raw): continue resolved_kind = edge_registry.resolve( e.get("kind", "related_to"), provenance=e.get("provenance", "explicit"), context={"file": file_path, "note_id": note_id} ) e["kind"] = resolved_kind e["origin_note_id"] = note_id e["virtual"] = False e["confidence"] = e.get("confidence", 1.0) # Volle Gewichtung # Registrierung der ID im Laufzeit-Schutz (Authority) edge_id = _mk_edge_id(resolved_kind, note_id, target_raw, e.get("scope", "note")) self.processed_explicit_ids.add(edge_id) final_edges.append(e) # PHASE 2: Symmetrische Kanten (Invers) mit Authority-Schutz erzeugen explicit_only = [x for x in final_edges if not x.get("virtual")] for e in explicit_only: kind = e["kind"] inverse_kind = edge_registry.get_inverse(kind) target_raw = e.get("target_id") # ID-Resolution target_ctx = self.batch_cache.get(target_raw) target_canonical_id = target_ctx.note_id if target_ctx else target_raw # Validierung für Symmetrie-Erzeugung (Kein Self-Loop, valide ID) if (inverse_kind and target_canonical_id and target_canonical_id != note_id and self._is_valid_note_id(target_canonical_id)): potential_id = _mk_edge_id(inverse_kind, target_canonical_id, note_id, e.get("scope", "note")) # AUTHORITY-CHECK: Batch-Gedächtnis oder Datenbank is_in_batch = potential_id in self.processed_explicit_ids is_in_db = False if not is_in_batch: # Real-Time DB Check verhindert 400 Bad Request durch vorherige ID-Validierung is_in_db = await is_explicit_edge_present(self.client, self.prefix, potential_id) if not is_in_batch and not is_in_db: if (inverse_kind != kind or kind not in ["related_to", "references"]): inv_edge = e.copy() inv_edge.update({ "note_id": target_canonical_id, "target_id": note_id, "kind": inverse_kind, "virtual": True, "provenance": "structure", "confidence": 1.0, # Gewichtung bleibt gleich laut Nutzerwunsch "origin_note_id": note_id }) final_edges.append(inv_edge) logger.info(f"🔄 [SYMMETRY] Built inverse: {target_canonical_id} --({inverse_kind})--> {note_id}") edges = final_edges # 4. DB Upsert if apply: if purge_before and old_payload: purge_artifacts(self.client, self.prefix, note_id) # Speichern n_name, n_pts = points_for_note(self.prefix, note_pl, None, self.dim) upsert_batch(self.client, n_name, n_pts) if chunk_pls and vecs: c_pts = points_for_chunks(self.prefix, chunk_pls, vecs)[1] upsert_batch(self.client, f"{self.prefix}_chunks", c_pts) if edges: e_pts = points_for_edges(self.prefix, edges)[1] upsert_batch(self.client, f"{self.prefix}_edges", e_pts) return { "path": file_path, "status": "success", "changed": True, "note_id": note_id, "chunks_count": len(chunk_pls), "edges_count": len(edges) } except Exception as e: logger.error(f"Processing failed: {e}", exc_info=True) return {**result, "error": str(e)} async def create_from_text(self, markdown_content: str, filename: str, vault_root: str, folder: str = "00_Inbox") -> Dict[str, Any]: """Erstellt eine Note aus einem Textstream.""" target_path = os.path.join(vault_root, folder, filename) os.makedirs(os.path.dirname(target_path), exist_ok=True) with open(target_path, "w", encoding="utf-8") as f: f.write(markdown_content) await asyncio.sleep(0.1) return await self.process_file(file_path=target_path, vault_root=vault_root, apply=True, force_replace=True, purge_before=True)