fix(saas): P2 code quality fixes + config PATCH/PUT alignment

P2 code quality (SEC2-P2-01~10):
- P2-04: Replace vague TODO with detailed Phase 2 design note in generate_embedding.rs
- P2-05: Add NOTE(fire-and-forget) annotations to 4 long-running tokio::spawn in main.rs
- P2-07: Add DESIGN NOTE to scheduler explaining sequential execution rationale
- P2-08: Add compile-time table name whitelist + runtime char validation in db.rs
- P2-02: Verified N/A (only zclaw-pipeline uses serde_yaml_bw, no inconsistency)
- P2-06: Verified N/A (bind loop correctly matches 6-column placeholders)
- P2-03: Remains OPEN (requires upstream sqlx release)

Config HTTP method alignment (B3-4):
- Fix admin-v2 config.ts: request.patch -> request.put to match backend .put() route
- Fix backend handler doc comment: PATCH -> PUT
- Add @reserved annotations to 6 config handlers without frontend callers

crates/zclaw-saas/src/workers/generate_embedding.rs

@@ -102,9 +102,11 @@ impl Worker for GenerateEmbeddingWorker {
             keywords.len(),
         );
 
-        // Phase 2: 如果配置了 embedding provider，在此处调用 embedding API
-        // 并更新 chunks 的 embedding 列
-        // TODO: let _ = generate_vectors(db, &args.item_id, &chunks).await;
+        // NOTE (Phase 2 - deferred): Embedding vector generation is not yet implemented.
+        // When pgvector is configured with an embedding provider, uncomment and implement:
+        //   generate_vectors(db, &args.item_id, &chunks).await
+        // This will call the configured embedding API and update knowledge_chunks.embedding column.
+        // See: docs/memory_pipeline_embedding_fix.md for the embedding configuration steps.
 
         Ok(())
     }