Files
kbdb-ingest-plugin/docs/3-specs/ingest-pipeline/tasks.md
T
Leo dffefdcdc2 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

46 lines
1.9 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# ingest pipeline — Tasks
> 唯一進度來源。狀態:[ ] 未開始 [🔄] 進行中 [x] 完成 [⏸] 卡住
> 跨專案藍圖:InkStoneCo `docs/3-specs/mira-dissolve/`。
## T0 repo 骨架(本輪)
- [x] 0.1 建 public repo `uncle6me-web/kbdb-ingest-plugin`
- [x] 0.2 CLAUDE.md(上游指針 + ingest 鐵律)+ README + .gitignore
- [x] 0.3 `contracts/ingest-candidate.json`(從頂層 SDD 複製,凍結契約)
- [x] 0.4 SDD 三件式骨架
- [ ] 0.5 package.json / tsconfig / wrangler.toml(參考 kbdb-graph-plugin
## T1 SourceAdapterR1
- [ ] 1.1 GitHub 拉 reporuntime API/clone,非 Actions
- [ ] 1.2 content-hashper-filesource.uri = github:owner/repo@path
- [ ] 1.3 被 KBDB MCP `refresh` 代轉觸發的接口
## T2 採取(R2,路徑 A 優先)
- [ ] 2.1 拉本地 CC 已建三元組 + gloss(用了 system-dev-template 的 repo
- [ ] 2.2 cherry-pick `polaris/mira/tools/_kbdb_client.py` → 改純餵食器(POST envelope,不寫 KBDB
## T3 extractR3,路徑 B fallback
- [ ] 3.1 cherry-pick `wiki_synthesis.yaml` classify / 兩 skill block
- [ ] 3.2 模型用戶可選 + 品質門檻白名單(預設 Haiku,深萃 Claude via CC
- [ ] 3.3 模型測試集(中文 + 人類暗示樣本,轉回歸測試)— deferred,先跑預設
- [ ] 3.4 JSON-fail 升級閘(淺萃失敗升 deep)
- [ ] 3.5 第一版不 embedembed 等 base vectorizeInkStoneCo T2.4
## T4 跨 repo 織網(R4,主職)
- [ ] 4.1 匯總多 repo 三元組
## T5 輸出 + CLIR5/R6
- [ ] 5.1 POST envelope 給 graph `POST /triplets/ingest`(嚴格符合 contract)⏸ 待 graph 寫入端(InkStoneCo T3.3
- [ ] 5.2 薄 ops CLI(手動重萃);不帶查詢 MCP
## 阻擋項
1. ⏸ T5.1 依賴 graph `POST /triplets/ingest`InkStoneCo T3,待 graph repo 實作)。
2. ⏸ embed 依賴 base vectorizeInkStoneCo T2.4)。第一版不 embed 可先動。