keyword cleanup: v2 engine, alias rule layer, LLM semantic suggestions

- build_review_bundle.py: 新增 _compute_percentile/_compute_growth,
  候选池从固定阈值改为百分位排名 + 增速因子 (v2 policy)
- term_cleanup_policy.json: 升级 v2 schema
- generate_term_cleanup_suggestions.py: 新增 _prepare_alias_suggestions,
  规则层输出 alias (大小写/单复数/分词变体)
- generate_term_cleanup_semantic_suggestions.py: 新增 LLM 语义建议脚本
  (DeepSeek API, 产出 semantic alias/stopword/promote)
- SKILL.md: 更新为 5 Phase 工作流程
- 首轮清洗 apply: interest 54, aliases 17组, stopwords 17个
- docs/design/keyword-cleanup-flow-overview.md: 流程文档
- plans/: 引擎设计方案

configs/filter_context.personal.json

@@ -27,13 +27,21 @@
     "Agent Skills",
     "AgentScope",
     "AI Agent",
+    "AI Coding Agent",
     "AliSQL",
+    "Anthropic",
+    "Claude",
     "Claude Code",
+    "CLAUDE.md",
+    "Context Engineering",
+    "Cursor",
     "DeepSeek",
     "FastAPI",
     "Gin",
     "Go",
     "gRPC",
+    "Harness Engineering",
+    "Hermes Agent",
     "Java",
     "Kafka",
     "Kubernetes",
@@ -49,13 +57,25 @@
     "RAG",
     "ReActAgent",
     "Redis",
+    "Skill",
+    "SKILL.md",
+    "Skills",
     "Spring",
     "SubAgent",
+    "TypeScript",
+    "Vibe Coding",
     "Workflow",
+    "上下文压缩",
+    "上下文工程",
+    "上下文管理",
     "云原生",
+    "代码审查",
     "可观测性",
     "向量数据库",
+    "多Agent协作",
+    "大模型",
     "微服务",
+    "渐进式披露",
     "知识库"
   ]
 }