init: kbdb-ingest-plugin 骨架

KBDB 堆疊的餵食器（最薄一層）：拉 GitHub repo → 採取/萃取三元組 → 餵 graph 寫入端 → 織跨 vault 的圖。 - CLAUDE.md：上游指針 + ingest 鐵律（純餵食器/不碰儲存/不算向量/ 不帶查詢 MCP/部署繞 Actions/三守則） - README：定位 + 護城河命題（跨 vault 的圖） - contracts/ingest-candidate.json：凍結 envelope 契約（與 graph repo 同份） - docs/3-specs/ingest-pipeline/：SDD 三件式骨架（藍圖指向 InkStoneCo mira-dissolve） Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 12:43:26 +08:00
commit dffefdcdc2
7 changed files with 313 additions and 0 deletions
@@ -0,0 +1,104 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "IngestCandidateEnvelope",
+  "description": "ingest 插件 → graph 插件 的唯一邊界契約。一個 envelope = 一個來源檔(canonical MD)一次萃取的產物。graph 收下後負責正規化/clusters/bridge_score/embed,並以『翻 triplet template 實例的 status slot』做取代:同 source.uri 出新 content_hash 時,graph 把舊 active 實例 PATCH 成 deprecated、append 新批 active(可查、可 rollback、可清),ingest 對這些一無所知。注意:這是【輸入候選】,不是【已存三元組】(後者見 triplet.json)。",
+  "type": "object",
+  "required": ["source", "extractor", "triplets"],
+  "additionalProperties": false,
+  "properties": {
+    "source": {
+      "type": "object",
+      "description": "這批候選來自哪個 canonical MD。同時是『指回原文的指標』與『append-only 快照鍵』。",
+      "required": ["uri", "content_hash"],
+      "additionalProperties": false,
+      "properties": {
+        "uri": {
+          "type": "string",
+          "minLength": 1,
+          "description": "來源的穩定識別 = 快照鍵 + get_source 指標。格式: 'github:<owner>/<repo>@<path>' 例如 'github:uncle6me-web/LLM-Wiki-for-n8n@.claude/wiki/graph-rag.md'。同一 uri 的後續 envelope 會【取代】(latest-wins)前一批,而非疊加。"
+        },
+        "content_hash": {
+          "type": "string",
+          "minLength": 1,
+          "description": "來源檔內容的 hash(快照鍵)。graph 比對: 與該 uri 現存快照同 hash → no-op 跳過;不同 → 寫新快照。"
+        },
+        "anchor": {
+          "type": "string",
+          "description": "檔內定位(heading slug / block id),供 get_source 精準回跳。選填。"
+        },
+        "commit": {
+          "type": "string",
+          "description": "git commit sha(可追溯)。選填。"
+        },
+        "block_id": {
+          "type": "string",
+          "description": "向後相容: Logseq Block ID(= 既有 triplet.json 的 source_block_id)。非 git 來源時用。選填。"
+        }
+      }
+    },
+    "extractor": {
+      "type": "object",
+      "description": "萃取出處。供『升級率』觀測與『要不要重萃』判斷;不影響圖結構。",
+      "required": ["model", "tier"],
+      "additionalProperties": false,
+      "properties": {
+        "model": {
+          "type": "string",
+          "minLength": 1,
+          "description": "產生這批的模型,例如 'workers-ai/@cf/...' 或 'claude-sonnet-4-6'。"
+        },
+        "tier": {
+          "type": "string",
+          "enum": ["shallow", "deep"],
+          "description": "shallow = Workers AI 淺萃;deep = Claude API 深萃(淺萃 JSON-fail/過稀時升級)。"
+        },
+        "extracted_at": {
+          "type": "integer",
+          "description": "萃取的 unix 時間(秒)。快照排序用。選填(graph 收件時可補)。"
+        }
+      }
+    },
+    "nodes": {
+      "type": "array",
+      "description": "節點層附帶資訊(選填)。entity_type 與 gloss 是【節點】屬性,不是【邊】屬性 → 放這裡,不放 triplets。graph 用 gloss 去 embed(每節點一句,不是裸詞)、用 entity_type 去 typing。",
+      "items": {
+        "type": "object",
+        "required": ["name"],
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "description": "節點名(須對應某 triplet 的 subject 或 object 原字面)。"
+          },
+          "gloss": {
+            "type": "string",
+            "description": "一句話描述,供 embedding。例如 'Graph RAG — 用關係遍歷檢索、保住異見的 RAG 變體'。選填(建議 deep tier 產出)。"
+          },
+          "entity_type": {
+            "type": "string",
+            "enum": ["person", "event", "product", "market", "org"],
+            "description": "節點類型提示。graph 最終決定;ingest 只提示。選填。"
+          }
+        }
+      }
+    },
+    "triplets": {
+      "type": "array",
+      "minItems": 1,
+      "description": "邊(關係)。ingest 只產原始 (s,p,o) + confidence。",
+      "items": {
+        "type": "object",
+        "required": ["subject", "predicate", "object"],
+        "additionalProperties": false,
+        "properties": {
+          "subject":   { "type": "string", "minLength": 1, "description": "主詞(實體名,須與 nodes[].name 對得上若有提供)" },
+          "predicate": { "type": "string", "minLength": 1, "description": "謂詞(關係)" },
+          "object":    { "type": "string", "minLength": 1, "description": "受詞(目標實體或值)" },
+          "confidence":{ "type": "number", "minimum": 0, "maximum": 1, "default": 1.0, "description": "萃取可信度。淺萃可附自評;graph 不據此過濾,只記錄。" }
+        }
+      }
+    }
+  },
+  "$comment": "禁止欄位(graph 領域,ingest 絕不可送): id / clusters / bridge_score / created_at / updated_at / 以及 triplet 上的 subject_entity_type|object_entity_type(類型只走 nodes[])。送了即違反 ingest=純餵食器的邊界,graph 應拒收或忽略。"
+}