app/core/ingestion/ingestion_note_payload.py

@@ -1,8 +1,11 @@
 """
 FILE: app/core/ingestion/ingestion_note_payload.py
 DESCRIPTION: Baut das JSON-Objekt für mindnet_notes. 
-FEATURES: Multi-Hash (body/full), Config-Fix für chunking_profile.
+FEATURES: 
-VERSION: 2.4.0
+  - Multi-Hash (body/full) für flexible Change Detection.
+  - Fix v2.4.2: edge_defaults Logik wiederhergestellt (DoD-Korrektur).
+VERSION: 2.4.2
+STATUS: Active
 """
 from __future__ import annotations
 from typing import Any, Dict, Tuple, Optional
@@ -12,7 +15,12 @@ import pathlib
 import hashlib
 import yaml
 
+# ---------------------------------------------------------------------------
+# Helper
+# ---------------------------------------------------------------------------
+
 def _as_dict(x) -> Dict[str, Any]:
+    """Versucht, ein ParsedMarkdown-ähnliches Objekt in ein Dict zu überführen."""
     if isinstance(x, dict): return dict(x)
     out: Dict[str, Any] = {}
     for attr in ("frontmatter", "body", "id", "note_id", "title", "path", "tags", "type", "created", "modified", "date"):
@@ -23,29 +31,53 @@ def _as_dict(x) -> Dict[str, Any]:
     return out
 
 def _ensure_list(x) -> list:
+    """Sichert, dass das Ergebnis eine Liste von Strings ist."""
     if x is None: return []
     if isinstance(x, list): return [str(i) for i in x]
     if isinstance(x, (set, tuple)): return [str(i) for i in x]
     return [str(x)]
 
 def _compute_hash(content: str) -> str:
+    """Berechnet einen SHA-256 Hash."""
     if not content: return ""
     return hashlib.sha256(content.encode("utf-8")).hexdigest()
 
 def _get_hash_source_content(n: Dict[str, Any], mode: str) -> str:
+    """Stellt den zu hashenden Content deterministisch zusammen."""
     body = str(n.get("body") or "")
     if mode == "body": return body
     if mode == "full":
         fm = n.get("frontmatter") or {}
         meta_parts = []
+        # Steuernde Metadaten für Change Detection
         for k in sorted(["title", "type", "status", "tags", "chunking_profile", "chunk_profile", "retriever_weight"]):
             val = fm.get(k)
             if val is not None: meta_parts.append(f"{k}:{val}")
-        return f" {'|'.join(meta_parts)}||{body}"
+        return f"{'|'.join(meta_parts)}||{body}"
     return body
 
+def _cfg_for_type(note_type: str, reg: dict) -> dict:
+    """Holt die typ-spezifische Konfiguration."""
+    if not isinstance(reg, dict): return {}
+    types = reg.get("types") if isinstance(reg.get("types"), dict) else reg
+    return types.get(note_type, {}) if isinstance(types, dict) else {}
+
+def _cfg_defaults(reg: dict) -> dict:
+    """Holt die globalen Default-Werte aus der Registry."""
+    if not isinstance(reg, dict): return {}
+    for key in ("defaults", "default", "global"):
+        v = reg.get(key)
+        if isinstance(v, dict): return v
+    return {}
+
+# ---------------------------------------------------------------------------
+# Haupt-API
+# ---------------------------------------------------------------------------
+
 def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
-    """Baut das Note-Payload inklusive Multi-Hash."""
+    """
+    Baut das Note-Payload inklusive Multi-Hash und edge_defaults.
+    """
     n = _as_dict(note)
     reg = kwargs.get("types_cfg") or {}
     hash_source = kwargs.get("hash_source", "parsed")
@@ -54,24 +86,48 @@ def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
     fm = n.get("frontmatter") or {}
     note_type = str(fm.get("type") or n.get("type") or "concept")
     
-    # Weights & Profiles
+    cfg_type = _cfg_for_type(note_type, reg)
-    retriever_weight = fm.get("retriever_weight", 1.0)
+    cfg_def = _cfg_defaults(reg)
-    chunk_profile = fm.get("chunking_profile") or fm.get("chunk_profile") or "sliding_standard"
+
+    # --- retriever_weight ---
+    retriever_weight = fm.get("retriever_weight")
+    if retriever_weight is None:
+        retriever_weight = cfg_type.get("retriever_weight", cfg_def.get("retriever_weight", 1.0))
+    try: retriever_weight = float(retriever_weight)
+    except: retriever_weight = 1.0
+
+    # --- chunk_profile ---
+    chunk_profile = fm.get("chunking_profile") or fm.get("chunk_profile")
+    if chunk_profile is None:
+        chunk_profile = cfg_type.get("chunking_profile", cfg_def.get("chunking_profile", "sliding_standard"))
+
+    # --- edge_defaults (WIEDERHERGESTELLT) ---
+    edge_defaults = fm.get("edge_defaults")
+    if edge_defaults is None:
+        edge_defaults = cfg_type.get("edge_defaults", cfg_def.get("edge_defaults", []))
+    edge_defaults = _ensure_list(edge_defaults)
+
+    # --- Basis-Metadaten ---
+    note_id = n.get("note_id") or n.get("id") or fm.get("id")
+    title = n.get("title") or fm.get("title") or ""
     
     payload: Dict[str, Any] = {
-        "note_id": n.get("note_id") or n.get("id") or fm.get("id"),
+        "note_id": note_id,
-        "title": n.get("title") or fm.get("title") or "",
+        "title": title,
         "type": note_type,
-        "path": str(n.get("path") or kwargs.get("path") or ""),
+        "path": str(n.get("path") or kwargs.get("file_path") or ""),
-        "retriever_weight": float(retriever_weight),
+        "retriever_weight": retriever_weight,
         "chunk_profile": chunk_profile,
+        "edge_defaults": edge_defaults, # Feld jetzt wieder enthalten
         "hashes": {}
     }
     
+    # --- MULTI-HASH ---
     for mode in ["body", "full"]:
         key = f"{mode}:{hash_source}:{hash_normalize}"
         payload["hashes"][key] = _compute_hash(_get_hash_source_content(n, mode))
 
+    # Metadaten-Felder
     if fm.get("tags") or n.get("tags"): payload["tags"] = _ensure_list(fm.get("tags") or n.get("tags"))
     if fm.get("aliases"): payload["aliases"] = _ensure_list(fm.get("aliases"))
     for k in ("created", "modified", "date"):