@clickzetta/cz-cli-darwin-arm64 0.3.32 → 0.3.35
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bin/cz-cli +0 -0
- package/bin/skills/cz-cli/SKILL.md +68 -4
- package/package.json +1 -1
package/bin/cz-cli
CHANGED
|
Binary file
|
|
@@ -7,15 +7,61 @@ description: "Route ALL ClickZetta Lakehouse operations to cz-cli: SQL, Studio t
|
|
|
7
7
|
|
|
8
8
|
You have no direct Lakehouse access. Always delegate via cz-cli.
|
|
9
9
|
|
|
10
|
+
## Capabilities
|
|
11
|
+
|
|
12
|
+
### SQL & Data Operations
|
|
13
|
+
- Execute any SQL against Lakehouse: SELECT, DDL (CREATE/ALTER/DROP TABLE, SCHEMA, VIEW), DML (INSERT, UPDATE, DELETE, MERGE INTO)
|
|
14
|
+
- Run async jobs and fetch results
|
|
15
|
+
- Preview table data and row counts
|
|
16
|
+
|
|
17
|
+
### Table & Schema Management
|
|
18
|
+
- List, describe, create, and drop tables and schemas
|
|
19
|
+
- View table history, indexes, partitions, and statistics
|
|
20
|
+
- Add or update column/table comments
|
|
21
|
+
- Create Dynamic Tables for auto-incremental ETL (ODS→DWD→DWS pipelines)
|
|
22
|
+
- Create Materialized Views for pre-computed aggregations
|
|
23
|
+
- Create Table Streams to capture INSERT/UPDATE/DELETE changes for CDC UPSERT
|
|
24
|
+
|
|
25
|
+
### Studio Task Management
|
|
26
|
+
- Create, configure, deploy, and delete Studio tasks (SQL, Shell, Python, integration, flow)
|
|
27
|
+
- Save task content and cron schedule
|
|
28
|
+
- Deploy, undeploy, and execute tasks ad-hoc
|
|
29
|
+
- Monitor run instances: list, detail, wait, logs, stop, rerun, backfill
|
|
30
|
+
- View run statistics and dependencies
|
|
31
|
+
|
|
32
|
+
### Data Sync Pipelines
|
|
33
|
+
- Create single-table realtime CDC sync tasks (MySQL/PostgreSQL/SQL Server → Lakehouse, task_type=28)
|
|
34
|
+
- Create multi-table or whole-database CDC sync tasks — mirror, merge, or sharded-table consolidation (task_type=281)
|
|
35
|
+
- Create offline batch sync tasks with Cron scheduling — single-table (task_type=10) or multi-table (task_type=291)
|
|
36
|
+
- Manage sync task lifecycle: start, stop, offline, backfill, add tables, re-sync individual tables
|
|
37
|
+
|
|
38
|
+
### Data Ingestion Pipelines
|
|
39
|
+
- Create continuous OSS/S3/COS ingest PIPE (LIST_PURGE scan mode or EVENT_NOTIFICATION mode)
|
|
40
|
+
- Create continuous Kafka ingest PIPE using READ_KAFKA function
|
|
41
|
+
- One-shot file import from URL, local path, or Volume (COPY INTO)
|
|
42
|
+
- Manage PIPE lifecycle: pause, resume, adjust batch interval, view load history
|
|
43
|
+
|
|
44
|
+
### Data Recovery
|
|
45
|
+
- Query data at a historical point in time (Time Travel: TIMESTAMP AS OF)
|
|
46
|
+
- Roll back a table to a previous version (RESTORE TABLE)
|
|
47
|
+
- Recover accidentally dropped tables, dynamic tables, or materialized views (UNDROP TABLE)
|
|
48
|
+
- Inspect change history (DESC HISTORY) and deleted objects (SHOW TABLES HISTORY)
|
|
49
|
+
- Configure retention: data_retention_days, data_lifecycle
|
|
50
|
+
|
|
51
|
+
### Connection & Environment Management
|
|
52
|
+
- Create, update, delete, and switch connection profiles (multi-cloud, multi-region)
|
|
53
|
+
- Check connection status and switch workspace
|
|
54
|
+
- List and test external data sources, browse catalogs and objects
|
|
55
|
+
- Generate Python SDK / ZettaPark / SQLAlchemy / JDBC connection code from profile parameters
|
|
56
|
+
|
|
10
57
|
## Route to cz-cli
|
|
11
58
|
|
|
59
|
+
- Any mention of cz-cli, ClickZetta, or Lakehouse
|
|
12
60
|
- SQL against Lakehouse (SELECT, DDL, DML)
|
|
13
61
|
- Studio task development, scheduling, monitoring
|
|
14
|
-
-
|
|
15
|
-
- Data pipelines (sync, import, CDC)
|
|
62
|
+
- Data pipelines (sync, import, CDC, streaming)
|
|
16
63
|
- Profile and connection configuration
|
|
17
64
|
- Performance analysis and optimization
|
|
18
|
-
- Any mention of cz-cli, ClickZetta, or Lakehouse
|
|
19
65
|
|
|
20
66
|
## Keep in host agent
|
|
21
67
|
|
|
@@ -23,12 +69,30 @@ You have no direct Lakehouse access. Always delegate via cz-cli.
|
|
|
23
69
|
- Local file operations, git
|
|
24
70
|
- Non-ClickZetta databases (PostgreSQL, MySQL standalone)
|
|
25
71
|
|
|
26
|
-
## Execution
|
|
72
|
+
## Execution strategy
|
|
73
|
+
|
|
74
|
+
**MANDATORY: Follow this order every time. No exceptions.**
|
|
75
|
+
|
|
76
|
+
**Step 1 — MUST check LLM first:**
|
|
77
|
+
|
|
78
|
+
```bash
|
|
79
|
+
cz-cli agent llm show
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
**Step 2 — If active LLM is configured (kind != "none"), you MUST use agent run:**
|
|
27
83
|
|
|
28
84
|
```bash
|
|
29
85
|
cz-cli agent run "<request>" --format a2a --dangerously-skip-permissions
|
|
30
86
|
```
|
|
31
87
|
|
|
88
|
+
Do NOT use direct cz-cli subcommands when an active LLM is available. Always delegate the full request to `cz-cli agent run`.
|
|
89
|
+
|
|
90
|
+
**Step 3 — ONLY if no active LLM (kind: "none" or empty list), fall back to direct commands:**
|
|
91
|
+
|
|
92
|
+
Decompose the request into concrete `cz-cli` subcommands (`sql`, `schema`, `table`, `task`, `runs`, `job`, `datasource`, `profile`, etc.), execute them, and synthesize the result.
|
|
93
|
+
|
|
94
|
+
Use direct commands for local setup and diagnostics even when agent path is available: `cz-cli profile ...`, `cz-cli -p <profile> status`, `cz-cli agent llm ...`, `cz-cli --help`.
|
|
95
|
+
|
|
32
96
|
With session continuity:
|
|
33
97
|
|
|
34
98
|
```bash
|