From 8f342ea2d392779e8236c5bdc07e6938d6888e14 Mon Sep 17 00:00:00 2001
From: Lars <Lars@stommer.de>
Date: Tue, 9 Sep 2025 16:15:05 +0200
Subject: [PATCH] schemas/chunk.schema.json aktualisiert

---
 schemas/chunk.schema.json | 106 ++++++++++++++++++++++++++++----------
 1 file changed, 79 insertions(+), 27 deletions(-)

diff --git a/schemas/chunk.schema.json b/schemas/chunk.schema.json
index 0c49b10..e992971 100644
--- a/schemas/chunk.schema.json
+++ b/schemas/chunk.schema.json
@@ -2,37 +2,89 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "title": "mindnet_chunk",
   "type": "object",
-  "required": ["id", "note_id", "chunk_index", "type", "path", "token_count", "lang"],
+  "description": "Chunk-Payload (Qdrant). Kompatibel mit Alt-Feldern und neuen Feldern für Export/Roundtrip.",
+  "required": ["id", "note_id", "chunk_index", "path"],
   "properties": {
-    "id": {"type": "string"},
-    "note_id": {"type": "string"},
-    "note_title": {"type": "string"},
-    "chunk_index": {"type": "integer"},
-    "char_start": {"type": "integer"},
-    "char_end": {"type": "integer"},
-    "token_count": {"type": "integer"},
-    "type": {"type": "string"},
-    "area": {"type": "string"},
-    "project": {"type": "string"},
-    "tags": {"type": "array", "items": {"type": "string"}},
-    "section_title": {"type": "string"},
-    "section_path": {"type": "string"},
-    "lang": {"type": "string"},
-    "wikilinks": {"type": "array", "items": {"type": "string"}},
-    "external_links": {"type": "array", "items": {"type": "string"}},
+    "id":           { "type": "string" },
+    "scope":        { "type": "string", "enum": ["chunk"] },
+    "note_id":      { "type": "string" },
+    "note_title":   { "type": "string" },
+    "note_type":    { "type": "string" },
+    "note_status":  { "type": "string" },
+    "type":         { "type": "string", "description": "Legacy: früherer Chunk-Typ; kann dem Note-Typ entsprechen" },
+    "area":         { "type": "string" },
+    "project":      { "type": "string" },
+    "tags":         { "type": "array", "items": { "type": "string" } },
+
+    "note_path":    { "type": "string" },
+    "path":         { "type": "string" },
+
+    "chunk_index":  { "type": "integer" },
+    "section_title":{ "type": ["string","null"] },
+    "section_path": { "type": ["string","null"] },
+
+    "char_start":   { "type": ["integer","null"] },
+    "char_end":     { "type": ["integer","null"] },
+    "char_len":     { "type": "integer" },
+
+    "token_count":  { "type": "integer", "description": "Legacy: frühere Token-Zahl" },
+    "token_est":    { "type": "integer", "description": "Neue grobe Token-Schätzung (≈ len(text)/4)" },
+
+    "neighbors": {
+      "type": "object",
+      "properties": {
+        "prev": { "type": ["string","null"] },
+        "next": { "type": ["string","null"] }
+      },
+      "additionalProperties": false
+    },
+
+    "text":         { "type": "string" },
+    "text_sha256":  { "type": "string", "pattern": "^sha256:[0-9a-fA-F]{64}$" },
+    "lang":         { "type": "string" },
+
+    "wikilinks":    { "type": "array", "items": { "type": "string" } },
+    "external_links": {
+      "type": "array",
+      "items": {
+        "anyOf": [
+          { "type": "string" },
+          {
+            "type": "object",
+            "properties": {
+              "href":  { "type": "string" },
+              "label": { "type": ["string","null"] }
+            },
+            "required": ["href"],
+            "additionalProperties": false
+          }
+        ]
+      }
+    },
     "references": {
       "type": "array",
-      "items": {"type": "object", "properties": {
-        "target_id": {"type": "string"},
-        "kind": {"type": "string"}
-      }, "required": ["target_id", "kind"]}
+      "items": {
+        "type": "object",
+        "properties": {
+          "target_id": { "type": "string" },
+          "kind":      { "type": "string" }
+        },
+        "required": ["target_id","kind"],
+        "additionalProperties": true
+      }
     },
-    "neighbors": {"type": "object", "properties": {
-      "prev": {"type": ["string","null"]},
-      "next": {"type": ["string","null"]}
-    }},
-    "path": {"type": "string"},
-    "created_at": {"type": "string"}
+
+    "embed_model":   { "type": "string" },
+    "embed_dim":     { "type": "integer" },
+    "embed_version": { "type": "integer" },
+
+    "created_at":   { "type": "string" }
   },
+
+  "allOf": [
+    { "anyOf": [ { "required": ["token_count"] }, { "required": ["token_est"] } ] },
+    { "anyOf": [ { "required": ["type"] }, { "required": ["note_type"] } ] }
+  ],
+
   "additionalProperties": true
 }