Rules

规则

Run all scripts from the skill root directory with
```
uv run scripts/<name>.py
```
.
Never print or log credential values — the SDK reads them from the environment.
Scripts that delete or mutate state require
```
--confirm
```
. Always pass it explicitly; never bypass it.
When the user does not specify a resource group, omit
```
--resource-group
```
so the SDK uses its configured default.
For LLM deployments: the scenario ID, executable ID, and model parameter names come from
```
genai-hub-foundation-models
```
— invoke it first if those values are unknown.
Deployment configuration naming convention: use
```
{executable_id}--{model_name}
```
for LLM deployments (e.g.
```
azure-openai--gpt-4o-mini
```
). Before creating a configuration, check whether one with that name already exists via
```
get_configurations.py --scenario-id <id>
```
and reuse it to avoid duplicates.

在 skill 根目录中使用
```
uv run scripts/<name>.py
```
运行所有脚本。
绝不打印或记录 credential 值——SDK 会从环境变量中读取它们。
删除或变更状态的脚本需要
```
--confirm
```
。始终显式传入该参数；绝不能绕过它。
如果用户未指定 resource group，请省略
```
--resource-group
```
，让 SDK 使用其已配置的默认值。
对于 LLM deployment：scenario ID、executable ID 和 model 参数名来自
```
genai-hub-foundation-models
```
——如果这些值未知，请先调用
```
genai-hub-foundation-models
```
。
Deployment configuration 命名约定：LLM deployment 使用
```
{executable_id}--{model_name}
```
（例如
```
azure-openai--gpt-4o-mini
```
）。创建 configuration 前，请通过
```
get_configurations.py --scenario-id <id>
```
检查是否已存在同名 configuration，并复用它以避免创建重复项。

List / Inspect Scenarios

列出/检查 Scenario

bash

undefined

bash

undefined

List all scenarios

uv run scripts/get_scenarios.py

Inspect a specific scenario and its versions

uv run scripts/get_scenarios.py --scenario-id <id> uv run scripts/get_scenarios.py --scenario-id <id> --response-format detailed

JSON output for piping

uv run scripts/get_scenarios.py --json

---

uv run scripts/get_scenarios.py --json

---

List Executables

列出 Executable

bash

undefined

bash

undefined

List executables for a scenario

uv run scripts/get_executables.py --scenario-id <id>

Inspect a specific executable (includes parameters and input artifacts)

uv run scripts/get_executables.py --scenario-id <id> --executable-id <id> uv run scripts/get_executables.py --scenario-id <id> --executable-id <id> --response-format detailed

JSON output

uv run scripts/get_executables.py --scenario-id <id> --json


Parameters are only returned when inspecting a single executable (`--executable-id`). The list view returns id, name, and description only.

---

uv run scripts/get_executables.py --scenario-id <id> --json


只有在检查单个 executable（`--executable-id`）时才会返回参数。列表视图仅返回 id、name 和 description。

---

Configurations

Configuration

bash

undefined

bash

undefined

List configurations

uv run scripts/get_configurations.py uv run scripts/get_configurations.py --scenario-id <id> uv run scripts/get_configurations.py --response-format detailed uv run scripts/get_configurations.py --json

Inspect a specific configuration

uv run scripts/get_configurations.py --configuration-id <id>

Create a configuration (binds parameters to an executable)

uv run scripts/create_configuration.py
--name my-config
--scenario-id <id>
--executable-id <id>
--param modelName=gpt-4o
--param temperature=0.7


If a deployment fails or stays PENDING after several minutes, verify parameter names and values against the executable's declared parameters:

```bash
uv run scripts/get_executables.py --scenario-id <id> --executable-id <id> --response-format detailed

uv run scripts/create_configuration.py
--name my-config
--scenario-id <id>
--executable-id <id>
--param modelName=gpt-4o
--param temperature=0.7


如果 deployment 失败，或在数分钟后仍处于 PENDING 状态，请对照 executable 声明的参数验证参数名和值：

```bash
uv run scripts/get_executables.py --scenario-id <id> --executable-id <id> --response-format detailed

Deployments

Deployment

Deployments serve inference endpoints. The standard flow is: create (or reuse) a configuration, then create a deployment from it.

Deployment 用于提供 inference endpoint。标准流程是：创建（或复用）configuration，然后基于它创建 deployment。

Configuration naming convention

Configuration 命名约定

Always check whether a matching configuration already exists before creating one, to avoid duplicates:

bash

undefined

创建 configuration 前，务必检查是否已存在匹配的 configuration，以避免重复：

bash

undefined

Check existing configurations before creating

uv run scripts/get_configurations.py --scenario-id <scenario-id> --json | jq '.[] | select(.name == "<expected-name>")'


Naming convention:
- LLM: `{executable_id}--{model_name}` — e.g. `azure-openai--gpt-4o-mini`
- Orchestration: `orchestration`
- Custom: choose a descriptive name

uv run scripts/get_configurations.py --scenario-id <scenario-id> --json | jq '.[] | select(.name == "<expected-name>")'


命名约定：
- LLM：`{executable_id}--{model_name}`——例如 `azure-openai--gpt-4o-mini`
- Orchestration：`orchestration`
- Custom：选择一个描述性名称

LLM deployment (from genai-hub-foundation-models handoff)

LLM deployment（来自

genai-hub-foundation-models

handoff）

bash

undefined

bash

undefined

1. Create configuration (skip if one with this name already exists):

uv run scripts/create_configuration.py
--name azure-openai--gpt-4o-mini
--scenario-id foundation-models
--executable-id azure-openai
--param modelName=gpt-4o-mini
--param modelVersion=latest

2. Deploy:

uv run scripts/create_deployment.py --configuration-id <config-id> --wait

undefined

uv run scripts/create_deployment.py --configuration-id <config-id> --wait

undefined

Orchestration deployment

bash

undefined

bash

undefined

1. Create configuration (skip if "orchestration" config already exists):

uv run scripts/create_configuration.py
--name orchestration
--scenario-id orchestration
--executable-id orchestration

2. Deploy:

uv run scripts/create_deployment.py --configuration-id <config-id> --wait --timeout 600

undefined

uv run scripts/create_deployment.py --configuration-id <config-id> --wait --timeout 600

undefined

List and inspect deployments

列出并检查 Deployment

bash

undefined

bash

undefined

List all deployments

uv run scripts/get_deployments.py

Filter by status or scenario or executable

uv run scripts/get_deployments.py --status RUNNING uv run scripts/get_deployments.py --scenario orchestration uv run scripts/get_deployments.py --executable-id azure-openai --status RUNNING uv run scripts/get_deployments.py --executable-id azure-openai --status RUNNING --json

Inspect one deployment

uv run scripts/get_deployments.py --deployment-id <id> uv run scripts/get_deployments.py --deployment-id <id> --response-format detailed uv run scripts/get_deployments.py --deployment-id <id> --json

undefined

uv run scripts/get_deployments.py --deployment-id <id> uv run scripts/get_deployments.py --deployment-id <id> --response-format detailed uv run scripts/get_deployments.py --deployment-id <id> --json

undefined

Stop, patch, delete, logs

停止、patch、删除和日志

bash

undefined

bash

undefined

Stop a deployment

uv run scripts/stop_deployment.py --deployment-id <id> --confirm uv run scripts/stop_deployment.py --deployment-id <id> --confirm --wait

Patch (swap configuration on a running deployment)

uv run scripts/patch_deployment.py --deployment-id <id> --configuration-id <new-config-id>

Delete (must be STOPPED or DEAD first)

uv run scripts/delete_deployment.py --deployment-id <id> --confirm

Stop and delete in one step:

uv run scripts/delete_deployment.py --deployment-id <id> --confirm --auto-stop

Deployment logs

uv run scripts/get_deployment_logs.py --deployment-id <id> uv run scripts/get_deployment_logs.py --deployment-id <id> --tail 50 uv run scripts/get_deployment_logs.py --deployment-id <id> --order asc uv run scripts/get_deployment_logs.py --deployment-id <id> --json

Remove duplicate LLM deployments (only affects LLM deployments with a model name)

uv run scripts/dedup_deployments.py --dry-run uv run scripts/dedup_deployments.py

---

uv run scripts/dedup_deployments.py --dry-run uv run scripts/dedup_deployments.py

---

Handoffs

交接

Need a Bearer token or credential setup? → invoke
```
aicore-admin-resources
```
Need executable ID, model name, or model capabilities? → invoke
```
genai-hub-foundation-models
```
Want to list available models or providers? → invoke
```
genai-hub-foundation-models
```

需要 Bearer token 或 credential 设置？ → 调用
```
aicore-admin-resources
```
需要 executable ID、model name 或 model capabilities？ → 调用
```
genai-hub-foundation-models
```
想列出可用的 model 或 provider？ → 调用
```
genai-hub-foundation-models
```

aicore-lifecycle-management

Original

Translation

Rules

规则

List / Inspect Scenarios

列出/检查 Scenario

List all scenarios

List all scenarios

Inspect a specific scenario and its versions

Inspect a specific scenario and its versions

JSON output for piping

JSON output for piping

List Executables

列出 Executable

List executables for a scenario

List executables for a scenario

Inspect a specific executable (includes parameters and input artifacts)

Inspect a specific executable (includes parameters and input artifacts)

JSON output

JSON output

Configurations

Configuration

List configurations

List configurations

Inspect a specific configuration

Inspect a specific configuration

Create a configuration (binds parameters to an executable)

Create a configuration (binds parameters to an executable)

Deployments

Deployment

Configuration naming convention

Configuration 命名约定

Check existing configurations before creating

Check existing configurations before creating

LLM deployment (from genai-hub-foundation-models handoff)

LLM deployment（来自 genai-hub-foundation-models handoff）

1. Create configuration (skip if one with this name already exists):

1. Create configuration (skip if one with this name already exists):

2. Deploy:

2. Deploy:

Orchestration deployment

Orchestration deployment

1. Create configuration (skip if "orchestration" config already exists):

1. Create configuration (skip if "orchestration" config already exists):

2. Deploy:

2. Deploy:

List and inspect deployments

列出并检查 Deployment

List all deployments

List all deployments

Filter by status or scenario or executable

Filter by status or scenario or executable

Inspect one deployment

Inspect one deployment

Stop, patch, delete, logs

停止、patch、删除和日志

Stop a deployment

Stop a deployment

Patch (swap configuration on a running deployment)

Patch (swap configuration on a running deployment)

Delete (must be STOPPED or DEAD first)

Delete (must be STOPPED or DEAD first)

Stop and delete in one step:

Stop and delete in one step:

Deployment logs

Deployment logs

Remove duplicate LLM deployments (only affects LLM deployments with a model name)

Remove duplicate LLM deployments (only affects LLM deployments with a model name)

Handoffs

交接

LLM deployment（来自
`genai-hub-foundation-models`
handoff）