db(p11): rag_query_log + learning_episodes — RAG 自主學習迴圈基礎
All checks were successful
CD Pipeline / deploy (push) Successful in 3m30s

Operation Ollama-First v5.0 / Phase 11 RAG + 自主學習

migrations/027 — rag_query_log(每次 RAG 查詢的 audit log)
- query_text 4KB CHECK + 90 天保留
- VECTOR(1024) bge-m3 embedding (與 ai_insights 一致簽名)
- ivfflat lists=100 索引
- saved_call 欄位追蹤「成功攔截 LLM 呼叫」次數
- feedback_score 1-5(NULL=未反饋)
- 6 條 CHECK 含 chk_rag_saved_consistent

migrations/028 — learning_episodes(蒸餾池 → ai_insights 前哨)
- 8 狀態機:pending/approved/awaiting_review/rejected_*4/expired
- weight 0-1(>=0.8 觸發 PromotionGate Stage 4 人工驗收)
- 9 條 CHECK 含 chk_le_approved_consistent / chk_le_review_consistent
- partial index idx_le_status WHERE in (pending, awaiting_review)
- distilled_text 16KB 上限

docs/phase11_db_design — 設計文檔
- 6 大決策(兩表分離 / ivfflat / partial index / 軟連結 / 90天保留 / 應用層白名單)
- 6 大風險評估(R1 PII / R2 蒸餾失誤 / R3 ivfflat 退化 / R4 dangling FK / R5/R6 trade-off)
- Phase 11 上線後驗收 SQL(EXPLAIN ANALYZE)

PromotionGate 4 階段(v5.0 護欄 #1, ADR-033):
  Stage 1: quality_score >= 0.7
  Stage 2: 無幻覺檢測(規則引擎,零 LLM)
  Stage 3: 與既有 insight 相似度 < 0.95
  Stage 4: weight >= 0.8 必經 Telegram 👍/👎(24h 無回應 → expired)

A4 fullstack-engineer 同時在寫 services/rag_service.py + learning_pipeline.py,
service 完成後一起部署啟用。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
OoO
2026-05-03 23:39:47 +08:00
parent 943de8466c
commit 2f20d8d7ba
3 changed files with 502 additions and 0 deletions

View File

@@ -0,0 +1,169 @@
-- =============================================================================
-- Migration 028: learning_episodes — 蒸餾池 / 知識庫前哨
-- Operation Ollama-First v5.0 — Phase 11
-- 日期: 2026-05-03 台北
-- 對應戰役: ADR-029Hermes-First+ Phase 11 PromotionGate 4 階段過濾
-- =============================================================================
-- 說明:
-- LLM/MCP 結果先寫入 learning_episodes蒸餾池過 4 階段 PromotionGate
-- 才晉升 ai_insights知識庫主檔。設計目的
-- - 隔離未驗證內容,避免直接污染 RAG 召回語料
-- - 保留 raw + distilled方便事後重訓
-- - 高權重(>=0.8)走人工驗收,低權重走自動晉升
--
-- PromotionGate 狀態機:
-- pending
-- ├─[Stage 1: quality<0.7]→ rejected_quality
-- ├─[Stage 2: 規則檢測幻覺]→ rejected_hallucination
-- ├─[Stage 3: 與既有 insight cosine>0.95]→ rejected_duplicate
-- ├─[Stage 4a: weight<0.8 + 過 1-3]→ approved → 寫 ai_insights → insight_id 回填
-- └─[Stage 4b: weight>=0.8]→ awaiting_review → Telegram 推播
-- ├─[人工 👍]→ approved
-- ├─[人工 👎]→ rejected_human
-- └─[24h 無反饋]→ expired (weight 降為 0.5 重走 Stage 4a)
--
-- 設計決策:
-- 1. insight_id 軟連結(不加 FK—— ai_insights archive 不應 cascade 影響蒸餾池
-- 2. source_table + source_id 軟連結到 ai_calls / mcp_calls方便事後重訓溯源
-- 3. embedding 與 rag_query_log 同 1024 維,跨表 cosine 一致
-- 4. 不設 90 天保留蒸餾池長期保留approved/rejected_* 進冷儲檔由後續 ADR 定)
-- —— 短期內暴增風險:靠 partial index + monthly archive scheduler 控制
-- 5. promotion_status 用 VARCHAR(32) + CHECK 白名單;不上 ENUM 因新增狀態方便
-- 6. rejected_reason CHECK 強制 rejected_* 狀態必填,避免「沒原因的拒絕」
-- 7. human_approver 存 Telegram username 的 SHA1[:8],避免 PII 落地
--
-- 回滾腳本(緊急用):
-- DROP INDEX IF EXISTS idx_le_embedding;
-- DROP INDEX IF EXISTS idx_le_insight_id;
-- DROP INDEX IF EXISTS idx_le_episode_type;
-- DROP INDEX IF EXISTS idx_le_status;
-- DROP INDEX IF EXISTS idx_le_created_at;
-- DROP TABLE IF EXISTS learning_episodes;
-- =============================================================================
CREATE TABLE IF NOT EXISTS learning_episodes (
id BIGSERIAL PRIMARY KEY,
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
-- 來源類型
-- mcp_result = MCP server 抓回的事實grounding / search / db query
-- llm_response = LLM 生成的洞察 / 摘要hermes_analyst / openclaw 等)
-- user_feedback = 用戶 Telegram 直接告知的事實(高 weight需人工確認
-- manual_curated = 人工手動入庫(最高 weight跳 PromotionGate
episode_type VARCHAR(32) NOT NULL,
-- 軟連結來源(不加 FK
source_table VARCHAR(32), -- 'ai_calls' / 'mcp_calls' / NULL
source_id BIGINT, -- 對應 source_table 的 id
-- 蒸餾後的精煉文本≤16KBraw 不存在此表,由 source_table 透過 source_id 回查)
distilled_text TEXT NOT NULL,
embedding VECTOR(1024), -- 與 ai_insights / rag_query_log 同維
-- 蒸餾品質評分0-1
-- <0.7 → Stage 1 直接 rejected_quality
-- >=0.7 → 進 Stage 2-3
quality_score NUMERIC(4,3) NOT NULL DEFAULT 0.0,
-- 權重(影響晉升路徑)
-- <0.8 → Stage 4a 自動晉升
-- >=0.8 → Stage 4b 人工驗收
weight NUMERIC(4,3) NOT NULL DEFAULT 0.5,
-- PromotionGate 狀態(見上方狀態機)
promotion_status VARCHAR(32) NOT NULL DEFAULT 'pending',
-- 晉升結果
insight_id BIGINT, -- 晉升後對應 ai_insights.id軟連結無 FK
rejected_reason TEXT, -- promotion_status=rejected_* 時必填
human_approver VARCHAR(64), -- Telegram username SHA1[:8]
reviewed_at TIMESTAMPTZ,
-- ─────── 護欄 (對齊 critic-A11 風格) ───────
CONSTRAINT chk_le_quality CHECK (
quality_score BETWEEN 0 AND 1
),
CONSTRAINT chk_le_weight CHECK (
weight BETWEEN 0 AND 1
),
CONSTRAINT chk_le_episode_type CHECK (
episode_type IN ('mcp_result','llm_response','user_feedback','manual_curated')
),
CONSTRAINT chk_le_status CHECK (
promotion_status IN (
'pending','approved','awaiting_review',
'rejected_quality','rejected_hallucination','rejected_duplicate','rejected_human',
'expired'
)
),
CONSTRAINT chk_le_distilled_size CHECK (
octet_length(distilled_text) <= 16384
),
CONSTRAINT chk_le_rejected_reason CHECK (
(promotion_status NOT LIKE 'rejected_%') OR (rejected_reason IS NOT NULL)
),
-- approved 必須有 insight_id其他狀態不應有
CONSTRAINT chk_le_approved_consistent CHECK (
(promotion_status = 'approved') = (insight_id IS NOT NULL)
),
-- source_table + source_id 一致性(要嘛兩個都 NULL要嘛兩個都有
CONSTRAINT chk_le_source_consistent CHECK (
(source_table IS NULL AND source_id IS NULL)
OR (source_table IS NOT NULL AND source_id IS NOT NULL)
),
CONSTRAINT chk_le_source_table CHECK (
source_table IS NULL OR source_table IN ('ai_calls','mcp_calls')
),
-- 人工驗收時 reviewed_at 必填
CONSTRAINT chk_le_review_consistent CHECK (
(human_approver IS NULL) OR (reviewed_at IS NOT NULL)
)
);
-- ─────────────────────────────────────────────────────────────────────────────
-- 索引設計
-- ─────────────────────────────────────────────────────────────────────────────
-- (1) 時間範圍掃描(蒸餾池規模監控)
CREATE INDEX IF NOT EXISTS idx_le_created_at
ON learning_episodes (created_at DESC);
-- (2) 待處理佇列查詢PromotionGate worker / 人工驗收 dashboard
-- partial index 縮體積:只關心 pending / awaiting_review 兩種「活躍」狀態
CREATE INDEX IF NOT EXISTS idx_le_status
ON learning_episodes (promotion_status, created_at DESC)
WHERE promotion_status IN ('pending','awaiting_review');
-- (3) 來源類型分布報表
CREATE INDEX IF NOT EXISTS idx_le_episode_type
ON learning_episodes (episode_type, created_at DESC);
-- (4) insight_id 反查(從 ai_insights 反推蒸餾來源)
CREATE INDEX IF NOT EXISTS idx_le_insight_id
ON learning_episodes (insight_id)
WHERE insight_id IS NOT NULL;
-- (5) pgvector ivfflatStage 3 重複檢測 cosine query 主用)
CREATE INDEX IF NOT EXISTS idx_le_embedding
ON learning_episodes
USING ivfflat (embedding vector_cosine_ops)
WITH (lists = 100)
WHERE embedding IS NOT NULL;
-- ─────────────────────────────────────────────────────────────────────────────
-- 權限
-- ─────────────────────────────────────────────────────────────────────────────
GRANT ALL PRIVILEGES ON learning_episodes TO momo;
GRANT USAGE, SELECT ON SEQUENCE learning_episodes_id_seq TO momo;
-- 註: expired 狀態降權 worker24h 無反饋)由 scheduler 跑:
-- UPDATE learning_episodes
-- SET promotion_status='expired', weight=0.5
-- WHERE promotion_status='awaiting_review'
-- AND created_at < NOW() - INTERVAL '24 hours';
-- 之後由 PromotionGate Stage 4a 重跑該批 expired 走自動晉升路徑。
DO $$
BEGIN
RAISE NOTICE 'Migration 028 done: learning_episodes + 5 indexes + 9 CHECK constraints (Operation Ollama-First v5.0 P11)';
END $$;