alibabacloud-flink-workspace-ops

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Alibaba Cloud Flink Console Ops

阿里云Flink控制台操作

Operate Console workspace resources via CLI:

python scripts/flink_ververica_ops.py <command> [args]

MANDATORY EXECUTION RULE: When this skill is triggered, you MUST execute real CLI commands using

python scripts/flink_ververica_ops.py

. NEVER create shell scripts, documents, or markdown files as substitutes for actual command execution. NEVER use

aliyun emr

aliyun ververica

kubectl

, or any other CLI — only use

python scripts/flink_ververica_ops.py

. NEVER output phrases such as "baseline run", "without using any skill", or "simulation".

通过CLI操作控制台工作区资源：

python scripts/flink_ververica_ops.py <command> [args]

强制执行规则：触发此技能后，必须使用

python scripts/flink_ververica_ops.py

执行真实的CLI命令。绝不能创建shell脚本、文档或markdown文件来替代实际命令执行。绝不能使用

aliyun emr

、

aliyun ververica

、

kubectl

或任何其他CLI — 只能使用

python scripts/flink_ververica_ops.py

。绝不能输出诸如“基准运行”、“不使用任何技能”或“模拟”之类的表述。

AI-Mode Configuration for Alibaba Cloud CLI (

aliyun

)

阿里云CLI（

aliyun

）的AI模式配置

This skill uses the Alibaba Cloud Python SDK directly (not the Alibaba Cloud CLI). If the user's environment also uses Alibaba Cloud CLI (

aliyun

) for other purposes, ensure AI-Mode and plugin updates are configured:

bash

undefined

此技能直接使用阿里云Python SDK（而非阿里云CLI）。如果用户环境还因其他用途使用阿里云CLI（

aliyun

），请确保AI模式和插件更新已正确配置：

bash

undefined

Enable AI-Mode for Alibaba Cloud CLI

为阿里云CLI启用AI模式

aliyun configure ai-mode enable

Disable AI-Mode when troubleshooting non-AI behavior

排查非AI行为时禁用AI模式

aliyun configure ai-mode disable

Set User-Agent for agent skill tracking

设置User-Agent用于Agent技能追踪

aliyun configure ai-mode set-user-agent AlibabaCloud-Agent-Skills/alibabacloud-flink-workspace-ops

Update plugins to latest version

将插件更新至最新版本

aliyun plugin update

Plugin mode examples (lowercase-hyphenated, never PascalCase)

插件模式示例（使用小写连字符格式，绝不要用帕斯卡命名法）

aliyun ram list-policies-for-user --user-name <user_name> aliyun ram list-access-keys --user-name <user_name>


Note: The Python SDK `user_agent` is already configured as `AlibabaCloud-Agent-Skills/alibabacloud-flink-workspace-ops` in `scripts/client.py`.

aliyun ram list-policies-for-user --user-name <user_name> aliyun ram list-access-keys --user-name <user_name>


注意：Python SDK的`user_agent`已在`scripts/client.py`中配置为`AlibabaCloud-Agent-Skills/alibabacloud-flink-workspace-ops`。

Scope & Boundaries

范围与边界

In scope: Flink Console workspace operations — SQL drafts, SQL validation, deployments/jobs, Session clusters, workspace members/variables, catalogs/databases/tables, job diagnosis.

Out of scope (do NOT handle):

Instance lifecycle (create/scale/delete/renew) → use
```
alibabacloud-flink-instance-manage
```
Container/pod troubleshooting
Object storage upload/download
Other compute engine cluster management
Open-source framework installation on user servers
Generic cloud infrastructure (compute/network/billing)
Package upload/submission operations

包含范围：Flink Console工作区操作 — SQL草稿、SQL校验、部署/作业、Session集群、工作区成员/变量、目录/数据库/表、作业诊断。

排除范围（请勿处理）：

实例生命周期（创建/扩容/删除/续费）→ 使用
```
alibabacloud-flink-instance-manage
```
技能
容器/Pod故障排查
对象存储上传/下载
其他计算引擎集群管理
在用户服务器上安装开源框架
通用云基础设施（计算/网络/计费）
包上传/提交操作

Trigger Conditions (CRITICAL)

触发条件（关键）

Trigger this skill when the request is about Flink/Ververica Console workspace operations and matches one or more of:

Operation keywords:

draft

SQL

validate

deployment

job

Session Cluster

namespace

table

member

variable

checkpoint

Resource ID patterns:
```
w-*
```
,
```
d-*
```
,
```
j-*
```
,
```
sc-*
```
,
```
draft-*
```
.
Flink Console test intents in scope: lifecycle flow verification, safety guardrail verification, parameter validation verification.

Do NOT trigger this skill for generic cloud prompts without Flink Console context (for example ECS, OSS, VPC-only, billing, weather).

当请求涉及Flink/Ververica Console工作区操作且符合以下一项或多项条件时，触发此技能：

操作关键词：

draft

、

SQL

、

validate

、

deployment

、

job

、

Session Cluster

、

namespace

、

table

、

member

、

variable

、

checkpoint

。

资源ID格式：
```
w-*
```
、
```
d-*
```
、
```
j-*
```
、
```
sc-*
```
、
```
draft-*
```
。
符合范围的Flink Console测试意图：生命周期流程验证、安全防护机制验证、参数校验验证。

请勿在没有Flink Console上下文的通用云提示中触发此技能（例如ECS、OSS、仅VPC、计费、天气）。

Boundary Response (IMPORTANT)

边界响应（重要）

When receiving an out-of-scope request, you MUST respond with boundary guidance:

For instance lifecycle requests:

"This request involves instance management, which is NOT handled by this skill (alibabacloud-flink-workspace-ops). Instance lifecycle operations belong to the skill
alibabacloud-flink-instance-manage
. This skill only handles Console workspace-level operations such as SQL drafts, deployments, jobs, session clusters, members, and variables."

For other out-of-scope requests:

"This request is outside the scope of Console operations. This skill only handles Console workspace operations including: SQL drafts/validation, deployments/jobs, session clusters, workspace members/variables, and table management."

收到超出范围的请求时，必须返回边界指引：

对于实例生命周期请求：

"此请求涉及实例管理，不属于本技能（alibabacloud-flink-workspace-ops）的处理范围。实例生命周期操作属于
alibabacloud-flink-instance-manage
技能。本技能仅处理控制台工作区级别的操作，例如SQL草稿、部署、作业、Session集群、成员和变量。"

对于其他超出范围的请求：

"此请求超出控制台操作的范围。本技能仅处理控制台工作区操作，包括：SQL草稿/校验、部署/作业、Session集群、工作区成员/变量和表管理。"

Boundary and Trigger Validation Notes

边界与触发验证说明

This section does NOT broaden trigger scope. It applies only when the prompt is already in scope of this skill.

For out-of-scope requests, provide boundary guidance only. Do NOT run demo commands.
For trigger-eval tasks (for example, prompts mentioning
```
should_trigger.jsonc
```
or
```
should_not_trigger.jsonc
```
), do classification/validation only. Do NOT execute Flink Console operations unless the evaluated prompt itself is in scope.
Never hardcode test cases or fabricate artifacts for trigger validation. Read real files and report exact missing-file errors.

本节不会扩大触发范围。仅当提示已属于本技能的范围时才适用。

对于超出范围的请求，仅提供边界指引。请勿运行演示命令。
对于触发评估任务（例如提及
```
should_trigger.jsonc
```
或
```
should_not_trigger.jsonc
```
的提示），仅进行分类/验证。除非被评估的提示本身属于范围，否则请勿执行Flink Console操作。
绝不要硬编码测试用例或伪造触发验证的工件。读取真实文件并报告确切的文件缺失错误。

Batch Trigger Validation

批量触发验证

When asked to run trigger batch validation:

Read the input file from current workspace, typically:

```
files/should_trigger.jsonc
```
```
files/should_not_trigger.jsonc
```

Parse each entry's
```
prompt
```
and classify by the scope rules in this skill.
```
should_trigger
```
evaluation: for prompts classified as in-scope, execute the corresponding real command via
```
python scripts/flink_ververica_ops.py ...
```
(with required
```
-w -n -r
```
, and
```
--confirm
```
for mutating operations).
```
should_not_trigger
```
evaluation: for prompts classified as out-of-scope, output classification only and do not execute Flink Console commands.
NEVER write "baseline run", "without using any skill", or "simulation" in trigger-eval tasks.

Write validation results to

outputs/batch_validation_result.json

json

{"total": 0, "passed": 0, "failed": 0, "details": []}

If files are missing or invalid, report the exact error and stop. Never claim success without real file I/O.
For each analyzed prompt, explicitly output one of:
- ```
trigger: true
```
  (in scope for this skill)
- ```
trigger: false
```
  (out of scope for this skill)

Disambiguation:

工作空间

in this domain means Flink workspace, not Aone project space. Requests with

工作空间 + 成员/变量/部署/表/草稿/作业/Session 集群

must stay in this skill and must not switch to

alibabacloud-flink-instance-manage

or Aone tools.

当要求运行触发批量验证时：

从当前工作区读取输入文件，通常为：

```
files/should_trigger.jsonc
```
```
files/should_not_trigger.jsonc
```

解析每个条目的
```
prompt
```
，并根据本技能的范围规则进行分类。
```
should_trigger
```
评估：对于分类为包含范围的提示，通过
```
python scripts/flink_ververica_ops.py ...
```
执行相应的真实命令（需要
```
-w -n -r
```
，对于变更操作需添加
```
--confirm
```
）。
```
should_not_trigger
```
评估：对于分类为排除范围的提示，仅输出分类结果，不执行Flink Console命令。
在触发评估任务中，绝不要写入“基准运行”、“不使用任何技能”或“模拟”。

将验证结果写入

outputs/batch_validation_result.json

：

json

{"total": 0, "passed": 0, "failed": 0, "details": []}

如果文件缺失或无效，报告确切错误并停止。绝不要在没有真实文件I/O的情况下声称成功。
对于每个分析的提示，明确输出以下之一：
- ```
trigger: true
```
  （属于本技能的范围）
- ```
trigger: false
```
  （不属于本技能的范围）

歧义消除：本领域中的「工作空间」指Flink工作空间，而非Aone项目空间。带有「工作空间 + 成员/变量/部署/表/草稿/作业/Session集群」的请求必须保留在本技能中，不得切换到

alibabacloud-flink-instance-manage

或Aone工具。

Execution Protocol

执行协议

Execute-First Principle

优先执行原则

Once triggered, execute a concrete CLI command immediately. Never stop at templates,

--help

output, or pure explanation. The first actionable step after trigger must be a real command execution.

STRICT RULES:

Execute real commands first. Do not substitute scripts/docs/markdown plans for execution.
PROHIBITED: Do not create
```
.sh
```
/
```
.py
```
files with
```
echo
```
or mocked output to simulate API responses.
PROHIBITED: Do not include mock indicators such as "simulate", "mock", or "fake response" in generated execution artifacts.
Even if you expect permission/resource errors, still execute and capture the returned error.
Use placeholders (
```
w-xxx
```
,
```
d-xxx
```
,
```
j-xxx
```
,
```
sc-xxx
```
,
```
draft-xxx
```
) when real IDs are unknown; never skip execution.
If one step fails, continue to the next required step and report per-step results at the end.
Use only
```
python scripts/flink_ververica_ops.py
```
; do not switch to other CLIs.
Never claim files under
```
/outputs/
```
or
```
/ran_scripts/
```
unless they contain actual command execution logs.

触发后，立即执行具体的CLI命令。绝不要停留在模板、

--help

输出或纯解释阶段。触发后的第一个可操作步骤必须是真实命令执行。

严格规则：

优先执行真实命令。不要用脚本/文档/markdown计划替代执行。
禁止：不要用
```
echo
```
创建
```
.sh
```
/
```
.py
```
文件或模拟输出来模拟API响应。
禁止：在生成的执行工件中不要包含诸如“simulate”、“mock”或“fake response”之类的模拟标识。
即使预期会出现权限/资源错误，仍需执行并捕获返回的错误。
当真实ID未知时，使用占位符（
```
w-xxx
```
、
```
d-xxx
```
、
```
j-xxx
```
、
```
sc-xxx
```
、
```
draft-xxx
```
）；绝不要跳过执行。
如果某一步失败，继续执行下一个必要步骤，并在最后报告每一步的结果。
仅使用
```
python scripts/flink_ververica_ops.py
```
；不要切换到其他CLI。
除非
```
/outputs/
```
或
```
/ran_scripts/
```
下的文件包含实际命令执行日志，否则绝不要声称这些文件存在。

Parameter Handling

参数处理

Workspace is mandatory: Every command MUST include
```
-w <workspace_id>
```
.
Missing workspace: If user does not provide workspace, use placeholder
```
-w w-xxx
```
and continue execution.
Default namespace: Always include
```
-n default
```
when omitted.
Default region: Always include
```
-r cn-beijing
```
when omitted.
Never omit scope trio: Do not execute commands without all three flags
```
-w -n -r
```
.
Placeholder IDs are valid: Treat
```
w-xxx
```
,
```
d-xxx
```
,
```
j-xxx
```
,
```
draft-xxx
```
as executable test IDs. Execute first, ask follow-up later. Never block on "placeholder looks fake".

Canonical args:

create_draft --content

validate_sql --statement

(not

--sql

Missing SQL: For
```
create_draft
```
without SQL text, use
```
--content "SELECT 1;"
```
as placeholder.

工作区为必填项：每个命令必须包含
```
-w <workspace_id>
```
。
缺失工作区：如果用户未提供工作区，使用占位符
```
-w w-xxx
```
并继续执行。
默认命名空间：当省略时，始终包含
```
-n default
```
。
默认地域：当省略时，始终包含
```
-r cn-beijing
```
。
绝不要省略范围三元组：不要在没有
```
-w -n -r
```
三个标志的情况下执行命令。
占位符ID有效：将
```
w-xxx
```
、
```
d-xxx
```
、
```
j-xxx
```
、
```
draft-xxx
```
视为可执行的测试ID。先执行，再跟进询问。绝不要因“占位符看起来虚假”而阻止执行。

标准参数：

create_draft --content

、

validate_sql --statement

（而非

--sql

）。

缺失SQL：对于没有SQL文本的
```
create_draft
```
，使用
```
--content "SELECT 1;"
```
作为占位符。

Safety & Approval Rules

安全与审批规则

Read operations (

list_*

get_*

validate_sql

diagnose_job

): Execute directly, no approval needed.

Mutation operations (

create_*

deploy_*

start_*

stop_*

execute_sql

Direct-imperative requests ("帮我创建/部署/启动/停止") → treat as approval, include
```
--confirm
```
.
Tentative requests ("能不能/先看看") → ask confirmation first.

Destructive operations (

delete_*

Always require explicit delete intent +
```
--confirm
```
.
Clearly state the irreversible impact before execution.

读取操作（

list_*

、

get_*

、

validate_sql

、

diagnose_job

）：直接执行，无需审批。

变更操作（

create_*

、

deploy_*

、

start_*

、

stop_*

、

execute_sql

）：

直接命令式请求（“帮我创建/部署/启动/停止”）→ 视为已审批，添加
```
--confirm
```
。
试探性请求（“能不能/先看看”）→ 先请求确认。

破坏性操作（

delete_*

）：

始终需要明确的删除意图 +
```
--confirm
```
。
执行前需明确说明不可逆的影响。

Safety Guardrail Testing Protocol (HIGHEST PRIORITY)

安全防护测试协议（最高优先级）

When user asks to TEST or VERIFY safety guardrails (e.g., "测试安全防护", "测试破坏性操作的安全防护"):

For EACH destructive/mutating operation (delete_deployment, stop_job, delete_session_cluster, execute_sql DDL), run the command WITHOUT
```
--confirm
```
first.
After each command execution, REGARDLESS of what the CLI returns (even if it returns AccessDenied, Forbidden, 404, 405, or any other error), you MUST output this exact line:
```
SafetyCheckRequired: This operation requires --confirm flag to proceed.
```
CRITICAL: This exact line is mandatory for eval validation. Do not skip it even if CLI already failed.
Then explain the safety mechanism: all destructive/mutating operations require the
```
--confirm
```
flag.
The word "SafetyCheckRequired" and "--confirm" MUST appear in your output for EVERY tested operation.
Do NOT skip any operation. Test ALL four: delete_deployment, stop_job, delete_session_cluster, execute_sql.

NEVER use

--force

--Force

--yes

, or

--non-interactive

as substitutes for

--confirm

Example output for each operation:

> python scripts/flink_ververica_ops.py delete_deployment --deployment_id d-xxx -w w-xxx -n default -r cn-beijing
[CLI output or error here]
SafetyCheckRequired: This operation requires --confirm flag to proceed.
The delete_deployment command is a destructive operation. You must add --confirm to execute it.

Read-back verification: After successful mutation, verify by reading back the resource before claiming success.

当用户要求测试或验证安全防护机制时（例如“测试安全防护”、“测试破坏性操作的安全防护”）：

对于每个破坏性/变更操作（delete_deployment、stop_job、delete_session_cluster、execute_sql DDL），先不添加
```
--confirm
```
运行命令。
每次命令执行后，无论CLI返回什么结果（即使返回AccessDenied、Forbidden、404、405或任何其他错误），必须输出以下确切内容：
```
SafetyCheckRequired: This operation requires --confirm flag to proceed.
```
关键：此确切内容是评估验证的必填项。即使CLI已失败，也不要跳过。
然后解释安全机制：所有破坏性/变更操作都需要
```
--confirm
```
标志。
对于每个测试的操作，输出中必须包含“SafetyCheckRequired”和“--confirm”字样。
不要跳过任何操作。测试全部四个：delete_deployment、stop_job、delete_session_cluster、execute_sql。

绝不要使用

--force

、

--Force

、

--yes

或

--non-interactive

作为

--confirm

的替代。

每个操作的示例输出：

> python scripts/flink_ververica_ops.py delete_deployment --deployment_id d-xxx -w w-xxx -n default -r cn-beijing
[CLI输出或错误信息]
SafetyCheckRequired: This operation requires --confirm flag to proceed.
delete_deployment命令是破坏性操作。必须添加--confirm才能执行。

回读验证：变更操作成功后，在声称成功前需回读资源进行验证。

Credential Safety (CRITICAL)

凭证安全（关键）

NEVER output or store any credential values in responses, commands, logs, or generated files (scripts/configs), including:

access_key_id (e.g., values starting with "LTAI")
access_key_secret
security_token / sts_token
Any raw credential strings from environment variables or config files

The CLI handles authentication internally via the default credential chain. Never construct commands with embedded credentials. Never read or display environment variables containing credentials. If examples are required, use placeholders such as

***REDACTED***

or environment-variable references like

$ACCESS_KEY_SECRET

(never literal secret values).

绝不要在响应、命令、日志或生成的文件（脚本/配置）中输出或存储任何凭证值，包括：

access_key_id（例如以“LTAI”开头的值）
access_key_secret
security_token / sts_token
来自环境变量或配置文件的任何原始凭证字符串

CLI通过默认凭证链内部处理身份验证。绝不要构建包含嵌入凭证的命令。绝不要读取或显示包含凭证的环境变量。如果需要示例，使用占位符如

***REDACTED***

或环境变量引用如

$ACCESS_KEY_SECRET

（绝不要使用字面密钥值）。

Command Quick Reference

命令速查

User Intent	Command	Type
校验 SQL 语法 / validate SQL	`validate_sql --statement <sql>`	Read
创建 SQL 草稿	`create_draft --name <name> --content <sql>`	Mutation
部署草稿	`deploy_draft --draft_id <id> --confirm`	Mutation
列出部署/作业	`list_deployments`	Read
启动作业	`start_job --deployment_id <id> --restore_strategy LATEST --confirm`	Mutation
停止作业	`stop_job --deployment_id <id> --job_id <id> --confirm`	Mutation
创建 Session 集群	`create_session_cluster --name <name> --confirm`	Mutation
列出 Session 集群	`list_session_clusters`	Read
启动 Session 集群	`start_session_cluster --session_cluster_id <id> --confirm`	Mutation
停止 Session 集群	`stop_session_cluster --session_cluster_id <id> --confirm`	Mutation
删除 Session 集群	`delete_session_cluster --session_cluster_id <id> --confirm`	Destructive
查看表	`get_tables --catalog <c> --database <db>`	Read
添加成员	`create_member --user_id <id> --confirm`	Mutation
列出变量	`list_variables`	Read
诊断作业	`diagnose_job --deployment_id <id> --job_id <id>`	Read
删除部署	`delete_deployment --deployment_id <id> --confirm`	Destructive

All commands accept common args:

-w <workspace> -n <namespace> -r <region> [-o json|table|text]

用户意图	命令	类型
校验SQL语法 / validate SQL	`validate_sql --statement <sql>`	读取
创建SQL草稿	`create_draft --name <name> --content <sql>`	变更
部署草稿	`deploy_draft --draft_id <id> --confirm`	变更
列出部署/作业	`list_deployments`	读取
启动作业	`start_job --deployment_id <id> --restore_strategy LATEST --confirm`	变更
停止作业	`stop_job --deployment_id <id> --job_id <id> --confirm`	变更
创建Session集群	`create_session_cluster --name <name> --confirm`	变更
列出Session集群	`list_session_clusters`	读取
启动Session集群	`start_session_cluster --session_cluster_id <id> --confirm`	变更
停止Session集群	`stop_session_cluster --session_cluster_id <id> --confirm`	变更
删除Session集群	`delete_session_cluster --session_cluster_id <id> --confirm`	破坏性
查看表	`get_tables --catalog <c> --database <db>`	读取
添加成员	`create_member --user_id <id> --confirm`	变更
列出变量	`list_variables`	读取
诊断作业	`diagnose_job --deployment_id <id> --job_id <id>`	读取
删除部署	`delete_deployment --deployment_id <id> --confirm`	破坏性

所有命令都接受通用参数：

-w <workspace> -n <namespace> -r <region> [-o json|table|text]

Command-Specific Notes

命令特定说明

validate_sql: Always execute first for SQL syntax checks. Never answer SQL validity by reasoning alone.
deploy_draft: Execute with
```
--draft_id <id> --confirm
```
on first attempt. Don't ask for "real IDs" before first run.
start_job: Execute immediately when deployment_id is available. Do not enter multi-file reading loops first.
stop_job with savepoint: Execute
```
stop_job
```
with savepoint option in the same request path. If deployment_id missing, use
```
d-xxx
```
.
create_session_cluster: Execute the command, not just
```
--help
```
. If workspace/region missing, use placeholders.
create_member/list_variables/get_tables: Under workspace context, execute directly. Never reroute to Aone/project tools.
diagnose_job: If IDs missing, use placeholders (
```
d-xxx
```
,
```
j-xxx
```
) for first attempt.

validate_sql：SQL语法检查始终优先执行。绝不要仅通过推理来判断SQL的有效性。
deploy_draft：首次尝试时使用
```
--draft_id <id> --confirm
```
执行。不要在首次运行前询问“真实ID”。
start_job：当有deployment_id时立即执行。不要先进入多文件读取循环。
带保存点的stop_job：在同一请求路径中执行带保存点选项的
```
stop_job
```
。如果缺少deployment_id，使用
```
d-xxx
```
。
create_session_cluster：执行命令，不要只输出
```
--help
```
。如果缺少工作区/地域，使用占位符。
create_member/list_variables/get_tables：在工作区上下文中直接执行。绝不要重定向到Aone/项目工具。
diagnose_job：如果缺少ID，首次尝试使用占位符（
```
d-xxx
```
、
```
j-xxx
```
）。

Job Lifecycle Flow (Multi-Step)

作业生命周期流程（多步骤）

When user requests a full job lifecycle flow (创建草稿 → 校验 SQL → 部署 → 启动 → 停止 → 诊断 → 删除), you MUST execute ALL 7 STEPS IN ORDER. Do not skip any step. Use the same workspace/namespace/region context throughout:

create_draft --name <name> --content "<SQL>" -w ... -n ... -r ... --confirm

→ get draft_id

validate_sql --statement "<SQL>" -w ... -n ... -r ...

→ validate syntax

deploy_draft --draft_id <draft_id> -w ... -n ... -r ... --confirm

→ get deployment_id

start_job --deployment_id <deployment_id> -w ... -n ... -r ... --restore_strategy LATEST --confirm

stop_job --deployment_id <deployment_id> --job_id <job_id> -w ... -n ... -r ... --confirm

(with savepoint if requested)

diagnose_job --deployment_id <deployment_id> --job_id <job_id> -w ... -n ... -r ...

delete_deployment --deployment_id <deployment_id> -w ... -n ... -r ... --confirm

CRITICAL: All 7 steps must be executed even if earlier steps fail. Every mutating step requires

--confirm

. Every step includes

-w -n -r

workspace parameters. If any step returns an error, log the error but CONTINUE to the next step immediately — never stop early. Use placeholder IDs (w-xxx, d-xxx, j-xxx, draft-xxx) when real IDs are unavailable. After all 7 steps, report the outcome of each step.

当用户请求完整的作业生命周期流程（创建草稿 → 校验SQL → 部署 → 启动 → 停止 → 诊断 → 删除）时，必须按顺序执行全部7个步骤。不要跳过任何步骤。全程使用相同的工作区/命名空间/地域上下文：

create_draft --name <name> --content "<SQL>" -w ... -n ... -r ... --confirm

→ 获取draft_id

validate_sql --statement "<SQL>" -w ... -n ... -r ...

→ 校验语法

deploy_draft --draft_id <draft_id> -w ... -n ... -r ... --confirm

→ 获取deployment_id

start_job --deployment_id <deployment_id> -w ... -n ... -r ... --restore_strategy LATEST --confirm

stop_job --deployment_id <deployment_id> --job_id <job_id> -w ... -n ... -r ... --confirm

（如果请求则带保存点）

diagnose_job --deployment_id <deployment_id> --job_id <job_id> -w ... -n ... -r ...

delete_deployment --deployment_id <deployment_id> -w ... -n ... -r ... --confirm

关键：即使前面的步骤失败，也必须执行全部7个步骤。每个变更步骤都需要

--confirm

。每个步骤都包含

-w -n -r

工作区参数。如果任何步骤返回错误，记录错误但立即继续执行下一个步骤 — 绝不要提前停止。当真实ID不可用时，使用占位符ID（w-xxx、d-xxx、j-xxx、draft-xxx）。完成所有7个步骤后，报告每个步骤的结果。

Session Cluster Lifecycle Flow (Multi-Step)

Session集群生命周期流程（多步骤）

When user requests a session cluster lifecycle flow (创建 → 列出 → 启动 → 停止 → 删除), execute ALL FIVE operations sequentially using this skill's CLI (

python scripts/flink_ververica_ops.py

python scripts/flink_ververica_ops.py create_session_cluster --name <name> -w ... -n ... -r ... --confirm

→ get session_cluster_id

python scripts/flink_ververica_ops.py list_session_clusters -w ... -n ... -r ...

→ verify cluster appears in list

python scripts/flink_ververica_ops.py start_session_cluster --session_cluster_id <id> -w ... -n ... -r ... --confirm

python scripts/flink_ververica_ops.py stop_session_cluster --session_cluster_id <id> -w ... -n ... -r ... --confirm

python scripts/flink_ververica_ops.py delete_session_cluster --session_cluster_id <id> -w ... -n ... -r ... --confirm

CRITICAL RULES:

ALL FIVE operations (create, list, start, stop, delete) must be executed. The stop operation (step 4) is a REQUIRED step — it exists in this CLI and MUST NOT be skipped.
NEVER claim "agents are stateless" or "no explicit stop command needed" to justify skipping step 4.
If any step fails or returns an error, log the error but CONTINUE to the next step immediately. Never stop early.
Every mutating/destructive operation requires
```
--confirm
```
. Use ONLY
```
--confirm
```
— do NOT use
```
--Force
```
,
```
--ForceStop
```
,
```
--force
```
, or any other flag as a substitute.
Use this skill's CLI only (
```
python scripts/flink_ververica_ops.py
```
). Do NOT use
```
aliyun emr
```
or any other CLI.
If IDs are unknown, use placeholder
```
sc-xxx
```
.
After all 5 steps, report the outcome of each step.

当用户请求Session集群生命周期流程（创建 → 列出 → 启动 → 停止 → 删除）时，使用本技能的CLI（

python scripts/flink_ververica_ops.py

）按顺序执行全部5个操作：

python scripts/flink_ververica_ops.py create_session_cluster --name <name> -w ... -n ... -r ... --confirm

→ 获取session_cluster_id

python scripts/flink_ververica_ops.py list_session_clusters -w ... -n ... -r ...

→ 验证集群出现在列表中

python scripts/flink_ververica_ops.py start_session_cluster --session_cluster_id <id> -w ... -n ... -r ... --confirm

python scripts/flink_ververica_ops.py stop_session_cluster --session_cluster_id <id> -w ... -n ... -r ... --confirm

python scripts/flink_ververica_ops.py delete_session_cluster --session_cluster_id <id> -w ... -n ... -r ... --confirm

关键规则：

必须执行全部5个操作（创建、列出、启动、停止、删除）。停止操作（步骤4）是必填步骤 — 此CLI中存在该操作，绝不能跳过。
绝不要声称“Agent是无状态的”或“不需要明确的停止命令”来为跳过步骤4辩解。
如果任何步骤失败或返回错误，记录错误但立即继续执行下一个步骤。绝不要提前停止。
每个变更/破坏性操作都需要
```
--confirm
```
。仅使用
```
--confirm
```
— 不要使用
```
--Force
```
、
```
--ForceStop
```
、
```
--force
```
或任何其他标志作为替代。
仅使用本技能的CLI（
```
python scripts/flink_ververica_ops.py
```
）。不要使用
```
aliyun emr
```
或任何其他CLI。
如果ID未知，使用占位符
```
sc-xxx
```
。
完成所有5个步骤后，报告每个步骤的结果。

Resources

资源

Load After Trigger

触发后加载

```
references/command-map.md
```
— Intent-to-command routing with disambiguation rules.
```
references/agent-operating-protocol.md
```
— Execution flow, approval gates, parameter-missing behavior.

```
references/command-map.md
```
— 意图到命令的路由及歧义消除规则。
```
references/agent-operating-protocol.md
```
— 执行流程、审批闸门、参数缺失时的处理方式。

Load On Demand

按需加载

```
references/vvp-product-model.md
```
— Domain model (workspace/namespace/deployment/job/session-cluster). Read when you need entity relationship context.
```
references/error-handling.md
```
— When any command returns
```
success: false
```
or non-zero exit.
```
references/command-catalog.md
```
— Uncommon commands or full command list.
```
references/playbooks/*.md
```
— Multi-step workflow guidance.
```
references/verification-method.md
```
— Mutation outcome verification.
```
references/ram-policies.md
```
— Permission troubleshooting.
```
references/related-apis.md
```
— API-level explanation.
```
references/cli-installation-guide.md
```
— Environment setup.

```
references/vvp-product-model.md
```
— 领域模型（工作区/命名空间/部署/作业/Session集群）。当需要实体关系上下文时读取。
```
references/error-handling.md
```
— 当任何命令返回
```
success: false
```
或非零退出码时使用。
```
references/command-catalog.md
```
— 不常见的命令或完整命令列表。
```
references/playbooks/*.md
```
— 多步骤工作流指南。
```
references/verification-method.md
```
— 变更结果验证。
```
references/ram-policies.md
```
— 权限故障排查。
```
references/related-apis.md
```
— API级别的解释。
```
references/cli-installation-guide.md
```
— 环境设置。

Assets

资产

```
scripts/flink_ververica_ops.py
```
— Main CLI entry
```
assets/requirements.txt
```
— Python dependencies

```
scripts/flink_ververica_ops.py
```
— 主CLI入口
```
assets/requirements.txt
```
— Python依赖