@clickzetta/cz-cli-darwin-x64 0.3.75 → 0.3.78

package/bin/skills/clickzetta-dynamic-table/sql-to-dt/references/sql2dt-workflow.md

@@ -0,0 +1,109 @@
+# SQL → Dynamic Table 完整转换工作流
+
+当用户给你一组 CREATE TABLE DDL 和 INSERT OVERWRITE SQL，要求转换为 Dynamic Table 时，按以下步骤顺序执行。
+
+每一步的详细规则在对应的 skill 文件中，你需要同时引用它们。
+
+## 工作流步骤
+
+### Step 1: 预处理输入
+
+从 INSERT OVERWRITE 文件中移除：
+- 所有 `ALTER TABLE` 语句
+- `ANALYZE TABLE` 语句
+- SQL 注释（`--` 和 `/* */`）
+
+保留：CREATE TABLE、INSERT OVERWRITE、WITH、SET、CREATE TEMPORARY FUNCTION。
+
+### Step 2: 占位符替换
+
+按 #[[file:sql2dt-placeholder-rules.md]] 中的规则：
+1. 统一占位符格式（`{{ }}` → `${ }`）
+2. 替换所有占位符为 `SESSION_CONFIGS()` 调用
+3. 处理 nodash 变量、日期运算、macros 函数
+4. 根据引号上下文决定处理方式（去引号 / CONCAT / 直接替换）
+
+### Step 3: 自引用检测
+
+按 #[[file:sql2dt-self-reference-rules.md]] 中的规则：
+1. 检查 INSERT OVERWRITE 目标表是否出现在 FROM/JOIN 中
+2. 如果是自引用表，标记并在后续步骤中添加注释、使用显式 schema
+
+### Step 4: 核心转换
+
+按 #[[file:sql2dt-conversion-rules.md]] 中的规则：
+1. 解析 CREATE TABLE DDL（提取列、分区、属性等）
+2. 解析 INSERT OVERWRITE（提取查询、分区类型）
+3. 组装 `CREATE OR REPLACE DYNAMIC TABLE ... AS SELECT ...`
+4. 注入静态分区值到 SELECT（智能引号处理）
+5. 合并表属性模板（默认 `data_lifecycle=15`）
+6. 处理 UNION ALL（每个分支独立注入）
+7. 日期函数后处理：将所有 `DATE_SUB/DATE_ADD` 统一转为 `sub_days`
+
+### Step 5: 列校验
+
+按 #[[file:sql2dt-column-validation-rules.md]] 中的规则：
+1. 计算 schema 列数和 SELECT 列数
+2. 验证两者相等
+3. 检查重复别名和缺失分区列
+4. UNION ALL 分支列数一致性检查
+
+### Step 6: 生成配套文件
+
+按 #[[file:sql2dt-refresh-rules.md]] 中的规则：
+1. 从 DDL 中提取所有 SESSION_CONFIGS 变量
+2. 生成当前周期 refresh 语句
+3. 生成上一周期 prev_refresh 语句
+4. 生成回填 backfill 语句
+
+### Step 7: 转换后改进建议
+
+DDL 生成完成后，对转换结果做以下检查，并主动向用户提出改进建议：
+
+**检查 1：非分区表 + 持续写入风险**
+
+按 #[[file:../best-practices/non-partitioned-merge-into-warning.md]] 中的判断逻辑：
+- 生成的 DT 是非分区表（无 `PARTITIONED BY` 也无 `SESSION_CONFIGS()`）
+- 且 SQL 中包含 `ROW_NUMBER() OVER (PARTITION BY ... ORDER BY ... DESC) WHERE rn = 1` 去重模式
+
+→ 满足条件时，使用该文档中的告警话术模板向用户发出风险提示，并建议改用 MERGE INTO + Table Stream 方案。
+
+**检查 2：SQL 性能优化机会**
+
+按 #[[file:../best-practices/performance-optimization.md]] 中的规则，扫描生成的 DT SQL：
+- 存在 `LEFT/RIGHT/FULL OUTER JOIN` → 提示如果业务允许，改用 INNER JOIN 可提升增量效率
+- 存在无 `PARTITION BY` 的窗口函数 → 提示添加 PARTITION BY，否则每次增量都全量重算
+- `GROUP BY` 使用了复杂表达式（如 `DATE_TRUNC`、`SUBSTR`）→ 提示考虑在上游预计算或拆分为多级 DT
+
+**检查 3：JOIN 中是否有维度表**
+
+按 #[[file:../best-practices/dimension-table-join-guide.md]] 中的推荐场景：
+- SQL 中存在 JOIN → 询问用户右侧表是否为低频变更的维度表（码表、字典表、配置表等）
+- 如果是 → 建议在 TBLPROPERTIES 中添加 `mv_const_tables` 配置，并说明其行为和数据一致性权衡
+
+## 输出清单
+
+对每个表，最终输出：
+
+| 文件 | 内容 | 条件 |
+|------|------|------|
+| `表名.sql` | Dynamic Table DDL | 始终生成 |
+| `表名_refresh.sql` | 当前周期 REFRESH 语句 | 始终生成 |
+| `表名_prev_refresh.sql` | 上一周期 REFRESH 语句 | 仅有分区变量时 |
+| `表名_backfill.sql` | 回填语句 | 仅有分区变量时 |
+
+## 快速判断路径
+
+```
+输入 DDL + INSERT OVERWRITE
+  │
+  ├─ 有占位符？ → Step 2 占位符替换
+  │
+  ├─ 自引用？ → Step 3 特殊处理
+  │
+  ├─ 有静态分区？ → Step 4 注入分区值到 SELECT
+  │
+  ├─ 有 UNION ALL？ → Step 4 每个分支独立注入
+  │
+  └─ 生成 DDL → Step 5 校验 → Step 6 生成配套文件 → Step 7 改进建议
+```

package/bin/skills/cz-cli/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: cz-cli
-description: "Route ALL ClickZetta Lakehouse operations to cz-cli: SQL, Studio tasks, tables, pipelines, profiles. Use when user mentions ClickZetta, Lakehouse, cz-cli, or needs profile/connection configuration."
+description: "Route ALL ClickZetta Lakehouse operations to cz-cli: SQL, Studio tasks, tables, pipelines, profiles. Use when user mentions ClickZetta, Lakehouse, cz-cli, or needs profile/connection lakehouse configuration."
 ---
 
 # cz-cli — ClickZetta Lakehouse Subagent
@@ -56,7 +56,6 @@ You have no direct Lakehouse access. Always delegate via cz-cli.
 
 ## Route to cz-cli
 
-- Any mention of cz-cli, ClickZetta, or Lakehouse
 - SQL against Lakehouse (SELECT, DDL, DML)
 - Studio task development, scheduling, monitoring
 - Data pipelines (sync, import, CDC, streaming)
@@ -87,6 +86,10 @@ cz-cli agent run "<request>" --format a2a --dangerously-skip-permissions
 
 Do NOT use direct cz-cli subcommands when an active LLM is available. Always delegate the full request to `cz-cli agent run`.
 
+The output includes a `session_id`. Use it to inspect the run:
+- `cz-cli agent session status <session_id>` — current state (`busy`/`retry` with `progress`, `idle` with `result`, or `error`)
+- `cz-cli agent export <session_id>` — full conversation (messages, tool calls, reasoning, text). Wait until `status` is `idle` before exporting; otherwise the conversation may still be in progress.
+
 **Step 3 — ONLY if no active LLM (kind: "none" or empty list), fall back to direct commands:**
 
 Decompose the request into concrete `cz-cli` subcommands (`sql`, `schema`, `table`, `task`, `runs`, `job`, `datasource`, `profile`, etc.), execute them, and synthesize the result.
@@ -101,6 +104,127 @@ cz-cli agent run "<request>" --format a2a --dangerously-skip-permissions --sessi
 
 Reuse `session_id` for follow-ups on the same topic. Omit `--session` to start fresh.
 
+## Async mode (non-TTY / long-running tasks)
+
+When running in non-TTY environments (e.g. as a subagent from Claude Code) or for long-running tasks, use async mode to avoid blocking:
+
+### Submit asynchronously
+
+```bash
+cz-cli agent run "<request>" --async --format a2a --dangerously-skip-permissions
+```
+
+Returns immediately with a session ID:
+```json
+{"session_id": "01JXF3K...", "status": "running", "message": "Session submitted asynchronously"}
+```
+
+Note: In non-TTY with `--format a2a` or `--format json`, async mode activates automatically (no `--async` flag needed).
+
+### Poll status
+
+```bash
+cz-cli agent session status <session_id>
+```
+
+While running:
+```json
+{"session_id": "01JXF3K...", "status": "busy", "progress": "$ cz-cli table list -o table"}
+```
+
+Other progress examples you may see during polling:
+- `"💭 Thinking..."` — LLM is reasoning
+- `"✏ Generating response..."` — LLM is writing the reply
+- `"✱ Grep \"error\" · 3 matches"` — running a search tool
+- `"↻ Retry (attempt 2)"` — retrying a failed LLM call (paired with a `retry` field describing the reason)
+
+When complete:
+```json
+{"session_id": "01JXF3K...", "status": "idle", "result": "Here are the results:\n..."}
+```
+
+The `result` field is the final text reply. For full conversation details (thinking, tool calls, intermediate text), use `cz-cli agent export <session_id>`.
+
+If the session does not exist:
+```json
+{"session_id": "ses_invalid", "error": "Session not found"}
+```
+(exits with code 1)
+
+### Retrieve full conversation (thinking + tool calls + text)
+
+```bash
+cz-cli agent export <session_id>
+```
+
+Returns complete session with all message parts:
+```json
+{
+  "info": { "id": "...", "title": "...", "time": {...} },
+  "messages": [
+    {
+      "info": { "role": "user" },
+      "parts": [{ "type": "text", "text": "original prompt" }]
+    },
+    {
+      "info": { "role": "assistant" },
+      "parts": [
+        { "type": "reasoning", "text": "thinking content..." },
+        { "type": "tool", "tool": "bash", "state": { "status": "completed", "input": {...}, "output": "..." } },
+        { "type": "text", "text": "final answer..." }
+      ]
+    }
+  ]
+}
+```
+
+Part types in export:
+- `reasoning` — LLM thinking/reasoning blocks
+- `tool` — tool calls with full input/output (bash, read, write, edit, glob, grep, etc.)
+- `text` — final text response
+- `step-start` / `step-finish` — step boundaries
+- `patch` — code diffs
+- `subtask` — delegated sub-tasks
+
+### Async workflow pattern
+
+```bash
+# 1. Submit
+SESSION=$(cz-cli agent run "complex analysis" --async --format a2a --dangerously-skip-permissions | jq -r '.session_id')
+
+# 2. Poll until done, printing progress along the way
+while true; do
+  STATUS=$(cz-cli agent session status $SESSION)
+  STATE=$(echo "$STATUS" | jq -r '.status')
+  if [ "$STATE" = "idle" ]; then
+    echo "$STATUS" | jq -r '.result'
+    break
+  fi
+  echo "$STATUS" | jq -r '.progress // empty'
+  sleep 5
+done
+
+# Need full conversation (thinking + tool calls)?
+cz-cli agent export $SESSION
+```
+
+### With session continuity (async)
+
+```bash
+# First turn
+SESSION=$(cz-cli agent run "describe sales table" --async --format a2a --dangerously-skip-permissions | jq -r '.session_id')
+# ... wait for completion ...
+
+# Follow-up turn on same session
+cz-cli agent run "now show row counts" --async --format a2a --dangerously-skip-permissions --session $SESSION
+```
+
+### Important notes for async mode
+
+- **Permissions:** Always use `--dangerously-skip-permissions` — async mode cannot handle interactive permission prompts
+- **Server requirement:** An agent runtime server must be running (or will be started automatically)
+- **Error handling:** If session is already busy, returns `{"error": "session busy"}`
+
 ## Multi-environment (profiles)
 
 When the user specifies an environment or profile (e.g. "use uat_test", "on the test instance"):

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@clickzetta/cz-cli-darwin-x64",
-  "version": "0.3.75",
+  "version": "0.3.78",
   "description": "cz-cli binary for macOS x64 (Intel)",
   "os": [
     "darwin"

package/bin/skills/cz-cli-inner/SKILL.md

@@ -1,109 +0,0 @@
----
-name: cz-cli-inner
-description: "ClickZetta Lakehouse operations via cz-cli. Use when the user needs SQL queries, Studio task management, table/schema operations, run monitoring, or job inspection."
----
-
-# cz-cli — ClickZetta Lakehouse Operations
-
-You have `cz-cli` available in PATH. Use it via bash to operate on ClickZetta Lakehouse.
-
-Run `cz-cli <command> --help` for detailed options on any command.
-
-## Command Reference
-
-```
-cz-cli sql "<statement>" [--sync] [--write]   Execute SQL (async by default, --sync waits for result)
-cz-cli sql status <job-id>                    Check async job status
-
-cz-cli schema list [--like <pattern>]         List schemas
-cz-cli schema describe <name>                 Describe a schema
-cz-cli schema create <name>                   Create a schema
-cz-cli schema drop <name>                     Drop a schema
-
-cz-cli table list [--schema <name>]           List tables
-cz-cli table describe <name>                  Describe table columns
-cz-cli table preview <name>                   Preview table data
-cz-cli table stats <name>                     Row count and job summary
-cz-cli table history [name]                   Show table history
-cz-cli table create "<ddl>"                   Create table from DDL
-cz-cli table drop <name>                      Drop a table
-
-cz-cli workspace current                      Show current workspace
-
-cz-cli task list                              List Studio tasks
-cz-cli task create <name> --type <TYPE>       Create task (SQL/PYTHON/SHELL/SPARK/FLOW)
-cz-cli task content <task>                    Get task script, config and params (draft)
-cz-cli task save-content <task> --file <f>    Save task script; use --params '{"key":"val","dt":"bizdate","yd":"$[yyyy-MM-dd,-1d]"}' to set params (system params like bizdate/sys_plan_day/sys_biz_datetime etc. auto-detected)
-cz-cli task save-config <task>                Save task non-cron config, like retry, dependency
-cz-cli task save-cron <task>                  Save task schedule config
-cz-cli task deps <task>                       Show task dependencies (draft)
-cz-cli task deploy <task>                     Publish/deploy a task (alias: online)
-cz-cli task undeploy <task>                   Undeploy a task, irreversible (alias: offline)
-cz-cli task execute <task>                    Execute ad-hoc; auto-uses saved manual params as defaults (--param KEY=VAL overrides); warns if unresolved ${placeholders} remain (SQL will fail, Python/Shell silently keeps literal string)
-cz-cli task delete <task>                     Delete draft/offline task
-cz-cli task flow dag <task>                   Get flow DAG
-cz-cli task flow create-node <task>           Add node to flow
-cz-cli task flow remove-node <task>           Remove node
-cz-cli task flow bind <task>                  Create dependency
-cz-cli task flow unbind <task>                Remove dependency
-cz-cli task flow node-detail <task>           Get node detail
-cz-cli task flow node-save <task>             Save node script
-cz-cli task flow node-save-config <task>      Save node config
-cz-cli task flow submit <task>                Publish flow
-cz-cli task flow instances <task>             List flow node instances
-
-cz-cli runs list [--task <name>]              List run instances
-cz-cli runs detail <id>                       Get run detail
-cz-cli runs wait <id>                         Poll until complete
-cz-cli runs logs <id>                         Get execution log
-cz-cli runs deps <task>                       Published dependencies
-cz-cli runs stop <id>                         Stop a running instance
-cz-cli runs refill <task> --from D --to D    Backfill date range. D accepts YYYY-MM-DD (day boundary) or YYYY-MM-DDTHH:MM:SS (exact datetime for hourly/minutely tasks)
-cz-cli runs rerun <id>                        Rerun failed instance
-cz-cli runs stats                             Run statistics summary
-
-cz-cli attempts list [id]                     List attempts for a run
-cz-cli attempts log [id]                      Get attempt log
-
-cz-cli job status <job-id>                    Job status/summary
-cz-cli job result <job-id>                    Fetch job result set
-
-cz-cli status                                 Check connection status
-cz-cli profile list                           List connection profiles
-
-cz-cli datasource list [--type <type>] [--name <filter>]
-                                              List external data sources (type: mysql/kafka/redis/postgresql/...)
-cz-cli datasource catalogs <name_or_id>      List catalogs (databases/topics/buckets) in a data source
-cz-cli datasource objects <name_or_id> <catalog>
-                                              List objects (tables/topics/collections) in a catalog
-cz-cli datasource describe <name_or_id> <catalog> <object>
-                                              Show object metadata (columns, types)
-cz-cli datasource test <name_or_id>          Test data source connectivity
-cz-cli datasource sample <name_or_id> <catalog> <object>
-                                              Get sample data from an object
-```
-
-## Output Formats
-
-- `--format json` (default) — single-line JSON, best for parsing
-- `--format toon` — line-per-field, good for `grep`/`head`
-- `--format table` / `--format csv` / `--format pretty` — human-readable
-- `--field <name>` — extract one field as raw text
-
-## Key Rules
-
-1. **SQL is async by default**. Use `--sync` for SELECT when you need data immediately.
-2. **Write operations require `--write` flag** (INSERT/UPDATE/DELETE/CREATE/DROP).
-3. **Always pass `--type` when creating tasks** (SQL/PYTHON/SHELL/SPARK/FLOW).
-4. **Flow tasks use `task flow *` commands exclusively** — never use `task save-content` or `task deploy` on flow nodes.
-5. **Paginated results**: `list` commands return page 1 only. Check `ai_message` in response for next-page hints.
-6. **State-changing operations** (deploy/undeploy/execute/delete/refill): confirm intent with user first.
-7. **Multi-environment**: use `--profile <name>` to target a specific environment.
-8. **On `NO_PROFILE` error**: guide user to run `cz-cli setup`.
-9. **补数/回填/重跑历史数据 → `runs refill`**: when user says "补数", "回填", "重跑历史", "backfill", "re-run historical data", use `cz-cli runs refill <task> --from YYYY-MM-DD --to YYYY-MM-DD`. This is under `runs`, NOT `task`.
-
-## Companion Skills
-
-When the task involves writing SQL or Python task code, load these skills for accuracy:
-- **lakehouse-doc** — SQL syntax, functions, data types, DDL/DML for ClickZetta dialect
-- **lakehouse-python-sdk** — Python/Shell task development, BulkLoad, IGS, connector

package/bin/skills/lakehouse-doc/SKILL.md

@@ -1,107 +0,0 @@
----
-name: lakehouse-doc
-description: "云器 Lakehouse 官方文档知识库。编写 SQL、查询语法/函数/数据类型、DDL/DML、动态表、权限、计算组、数据湖、AI 函数等 Lakehouse 相关问题时，必须查阅本 skill 的 references/ 目录。"
----
-
-# lakehouse-doc
-
-云器 Lakehouse 官方文档。根据用户问题在 `references/` 下按文件名定位对应文档。
-
-## references/ 目录结构
-
-```
-references/
-├── *.md                          # 778 篇主文档（按主题命名，见下方索引）
-├── eco_integration/              # 生态工具集成 (12 篇)
-│   ├── dbt.md, superset.md, datagrip-lakehouse.md, trino.md ...
-├── java_reference/               # Java SDK (5 篇)
-│   ├── java-sdk-summary.md, jdbc.md, realtime-upload.md, client.md ...
-├── python_reference/             # Python SDK (3 篇)
-│   ├── connector.md, sqlalchemy.md, python-sdk-summary.md
-├── opensource/                   # 开源工具 (1 篇)
-│   └── travel.md
-└── sql_functions/                # SQL 函数参考 (339 篇)
-    ├── aggregate_functions/      # 聚合函数 (52): count.md, sum.md, avg.md ...
-    ├── window_functions/         # 窗口函数 (19): row_number.md, rank.md, lag.md ...
-    ├── table_functions/          # 表函数 (9): table_changes.md ...
-    ├── context_functions/        # 上下文函数 (8): current_user.md ...
-    └── scalar_functions/         # 标量函数 (339)
-        ├── datetime_functions/   # 日期时间 (66)
-        ├── string_functions/     # 字符串 (70)
-        ├── math_functions/       # 数学 (55)
-        ├── nested_functions/     # 嵌套类型 (45)
-        ├── bitmap_functions/     # Bitmap (29)
-        ├── json_functions/       # JSON (14)
-        ├── conditional_functions/# 条件 (14)
-        ├── high_order_functions/ # 高阶 (12)
-        ├── vector_functions/     # 向量 (11)
-        ├── ip_functions/         # IP (6)
-        ├── search_functions/     # 搜索 (6)
-        ├── hash_functions/       # 哈希 (5)
-        ├── geo_functions/        # 地理 (3)
-        ├── bitwise_functions/    # 位运算 (2)
-        └── partition/            # 分区 (1)
-```
-
-## 文档索引（llms.txt）
-
-# 云器 Lakehouse 文档（LLM 导航）
-
-> 云器 Lakehouse 是全托管的湖仓一体架构平台，基于云原生设计理念从零打造。通过**存算分离**、**Serverless弹性架构**、**开放存储格式**和**AI优化工具**，为企业提供数据仓库、数据湖、实时处理与BI报表的统一平台。
-
-## 快速入门
-
-- [概览](https://www.yunqi.tech/documents/Overview): 介绍云器Lakehouse的存算分离架构、Serverless计算、开放数据格式及主要应用场景。
-- [产品概念](https://www.yunqi.tech/documents/Concepts): 介绍云器Lakehouse的存算分离架构、Serverless计算、开放数据格式及主要应用场景。
-- [入门指导](https://www.yunqi.tech/documents/Tutorials): 通过数据导入、SQL查询、数据可视化等步骤，快速完成从数据接入到分析展示的完整流程。
-
-## 使用指南
-
-- [Studio](https://www.yunqi.tech/documents/studio_manual): 通过Web界面进行数据开发与管理，支持连接数据源、SQL查询、作业编排、结果可视化和资产目录浏览。
-- [对象模型](https://www.yunqi.tech/documents/object_model_design): 介绍云器Lakehouse的对象模型核心概念，包括目录、数据库、表、视图、物化视图、函数和共享的定义与层级关系。
-- [数据采集](https://www.yunqi.tech/documents/Ingestion): 通过本地文件、数据库、Kafka等多种数据源导入数据，涵盖核心概念、配置步骤与操作示例。
-- [数据加工](https://www.yunqi.tech/documents/Transformation): 围绕"数据加工"说明核心概念、关键配置与典型操作步骤，并提供示例与注意事项。
-- [数据分析](https://www.yunqi.tech/documents/Analysis): 提供从数据导入、SQL查询到可视化分析的全流程操作指南，涵盖数据源连接、SQL语法、函数使用及结果导出。
-- [安全](https://www.yunqi.tech/documents/data_security): 提供用户管理、权限控制、审计日志等安全功能。
-- [数据分享](https://www.yunqi.tech/documents/data_share): 围绕"数据分享"说明核心概念、关键配置与典型操作步骤。
-- [私网连接](https://www.yunqi.tech/documents/connect_to_Lakehouse): 通过配置终端节点实现跨VPC或本地IDC与云上服务的私网安全访问。
-- [性能测试](https://www.yunqi.tech/documents/benchmark): 性能测试核心概念、关键配置与典型操作步骤。
-- [生态工具](https://www.yunqi.tech/documents/tools): 生态工具核心概念、关键配置与典型操作步骤。
-- [Insight](https://www.yunqi.tech/documents/Lakehouse_Insight): 通过连接云器Lakehouse数据源，创建数据集并拖拽生成BI报表与看板。
-
-## SQL手册
-
-- [SQL命令](https://www.yunqi.tech/documents/sql-reference): DDL、DML、DQL等SQL命令的完整语法参考。
-- [数据类型](https://www.yunqi.tech/documents/data-type): 精确数值、浮点数、字符串、日期时间、布尔值等数据类型定义。
-- [SQL函数](https://www.yunqi.tech/documents/functions): SQL函数核心概念与使用示例。
-- [SQL使用指南](https://www.yunqi.tech/documents/considerations-for-using-sql): SQL使用注意事项与最佳实践。
-
-## 开发手册
-
-- [Java SDK 参考](https://www.yunqi.tech/documents/java-sdk-refer): Java SDK 核心概念、关键配置与典型操作步骤。
-- [Python SDK 参考](https://www.yunqi.tech/documents/python-sdk-refer): Python SDK 核心概念、关键配置与典型操作步骤。
-
-## 实践教程
-
-- [高效管理对象和组织数据](https://www.yunqi.tech/documents/data_org): 数据对象创建管理，目录组织、权限、生命周期策略。
-- [数据导入导出实践](https://www.yunqi.tech/documents/practice_data_import_and_export): 多数据源导入导出操作步骤与示例。
-- [数据查询分析实践](https://www.yunqi.tech/documents/practice_data_analysis): 从数据导入到可视化分析的全流程操作指南。
-- [构建和运维ELT流程实践](https://www.yunqi.tech/documents/ELT_practice): 企业级ELT流水线构建，涵盖开发、测试、部署及故障恢复。
-- [优化计算资源](https://www.yunqi.tech/documents/OptimizingComputingResources): 计算组配置、弹性伸缩策略和资源监控。
-- [性能体验](https://www.yunqi.tech/documents/performence_test): 性能测试方法、优化建议与监控指标。
-- [构建 Modern Data Stack](https://www.yunqi.tech/documents/ModernDataStackWithEcosystemTools): 现代数据栈核心组件与架构模式。
-- [AI应用开发](https://www.yunqi.tech/documents/REMOTEFUNCTION): 从数据准备、模型训练到服务部署的AI应用开发流程。
-- [安全与合规审计](https://www.yunqi.tech/documents/security_compliance_audit_guide): 权限管理、SQL审计日志、数据脱敏策略及合规性配置。
-- [用量和费用管理](https://www.yunqi.tech/documents/cost_management): 用量明细、费用构成、计费模式与预算管理。
-
-## Lakehouse AI
-
-- [Lakehouse AI 概述](https://www.yunqi.tech/documents/LakehouseAI_overview): 非结构化数据管理、AI外部函数、多模态检索、Python开发框架及对话式分析。
-- [AI 的数据准备](https://www.yunqi.tech/documents/Server_data_for_AI): 向量检索、全文搜索与结构化数据分析的无缝结合。
-- [AI 函数](https://www.yunqi.tech/documents/AI_function_in_SQL): 创建和使用AI函数，支持Python/Java调用外部AI服务。
-- [Zettapark](https://www.yunqi.tech/documents/LakehousePythonZettapark): Python开发框架API参考。
-- [AI + BI 统一工作流](https://www.yunqi.tech/documents/unifiedWorkflow): 自然语言交互生成SQL查询与可视化。
-- [AI Gateway](https://www.yunqi.tech/documents/AIGateway): 统一接入、路由分发、负载均衡、限流熔断。
-- [DataGPT](https://www.yunqi.tech/documents/datagpt_intro): 自然语言提问直接生成SQL并获取可视化图表。
-- [Lakehouse MCP Server](https://www.yunqi.tech/documents/LakehouseMCPServer): 通过MCP将数据湖仓能力暴露给AI助手。
-- [AI 生态](https://www.yunqi.tech/documents/AI_eco): 与PyTorch、TensorFlow、MLflow、LangChain等集成。

package/bin/skills/lakehouse-doc/references/.gitattributes

@@ -1 +0,0 @@
-.topwrite/assets/** filter=lfs diff=lfs merge=lfs -text

package/bin/skills/lakehouse-doc/references/.gitlab-ci.yml

@@ -1,11 +0,0 @@
-pages:
-  stage: deploy
-  script:
-    - mkdir .public
-    - cp -r * .public
-    - mv .public public
-  artifacts:
-    paths:
-      - public
-  only:
-    - gh-pages