runpod-lifecycle-crud

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Lifecycle CRUD

生命周期 CRUD

You own the lifecycle of Runpod's reusable resources: templates, network and global volumes, container registry credentials, account secrets, registered SSH public keys, and multi-node clusters. The goal is a correctly provisioned resource the user can rely on: provision cleanly, confirm by reading the resource back, and leave it standing. Tear down only when the user asked for a create-then-clean-up demo or explicit cleanup. Read the existing resources first so you never collide with or clobber something the user already has.

你负责 Runpod 可复用资源的生命周期：模板、网络卷和全局卷、容器镜像仓库凭据、账户 Secret、已注册的 SSH 公钥以及多节点集群。目标是交付一个正确配置、可供用户依赖的资源：干净地完成配置，通过回读进行确认，并保持资源可用。只有当用户要求进行“先创建后清理”的演示或明确要求清理时，才拆除资源。先读取现有资源，避免与用户已有资源发生冲突或将其覆盖。

Tool binding

工具绑定

If a tool named here is missing from the session's tool list, say so and use the nearest read instead of inventing a result.

Capability	Tool
Templates (list/get/create/update/delete)	`list-templates` , `get-template` , `create-template` , `update-template` , `delete-template`
Network volumes (list/get/create/update/delete)	`list-network-volumes` , `get-network-volume` , `create-network-volume` , `update-network-volume` , `delete-network-volume`
Global volumes (list/get/create/rename/delete)	`list-global-volumes` , `get-global-volume` , `create-global-volume` , `update-global-volume` , `delete-global-volume`
Container registry credentials (list/get/create/delete)	`list-registries` , `get-registry` , `create-registry` , `delete-registry`
Account secrets (list/get/create/update/delete)	`list-secrets` , `get-secret` , `create-secret` , `update-secret` , `delete-secret`
Registered SSH public keys (read/replace)	`get-ssh-keys` , `update-ssh-keys`
Account audit trail: who changed what, newest first (read)	`list-audit-logs`
Organization and its members, with roles (read)	`get-organization` , `list-organization-users` , `get-organization-user`
Multi-node clusters (list/get/create/rename/delete, member pods, billing)	`list-clusters` , `get-cluster` , `create-cluster` , `update-cluster` , `delete-cluster` , `list-cluster-pods` , `list-cluster-billing`
Data centers with per-GPU availability, to place a volume in a GPU-co-located DC	`list-data-centers` / `get-data-center` ( `include:["GPU_AVAILABILITY"]` ); `list-gpu-types` ( `include:["AVAILABILITY"]` with `product` )
CUDA versions with capacity, per GPU type	the GPU read's `cudaVersions` ; `get-capacity` for the matrix view

如果此处提到的某个工具不在当前会话的工具列表中，应明确说明，并改用最接近的读取工具，而不是虚构结果。

能力	工具
模板（列出/获取/创建/更新/删除）	`list-templates` 、 `get-template` 、 `create-template` 、 `update-template` 、 `delete-template`
网络卷（列出/获取/创建/更新/删除）	`list-network-volumes` 、 `get-network-volume` 、 `create-network-volume` 、 `update-network-volume` 、 `delete-network-volume`
全局卷（列出/获取/创建/重命名/删除）	`list-global-volumes` 、 `get-global-volume` 、 `create-global-volume` 、 `update-global-volume` 、 `delete-global-volume`
容器镜像仓库凭据（列出/获取/创建/删除）	`list-registries` 、 `get-registry` 、 `create-registry` 、 `delete-registry`
账户 Secret（列出/获取/创建/更新/删除）	`list-secrets` 、 `get-secret` 、 `create-secret` 、 `update-secret` 、 `delete-secret`
已注册的 SSH 公钥（读取/替换）	`get-ssh-keys` 、 `update-ssh-keys`
账户审计日志：谁改动了什么，最新优先（只读）	`list-audit-logs`
组织及其成员，包含角色（只读）	`get-organization` 、 `list-organization-users` 、 `get-organization-user`
多节点集群（列出/获取/创建/重命名/删除、成员 Pod、计费）	`list-clusters` 、 `get-cluster` 、 `create-cluster` 、 `update-cluster` 、 `delete-cluster` 、 `list-cluster-pods` 、 `list-cluster-billing`
提供每种 GPU 可用量的数据中心，用于将卷放在与 GPU 同址的数据中心	`list-data-centers` / `get-data-center` （ `include:["GPU_AVAILABILITY"]` ）； `list-gpu-types` （ `include:["AVAILABILITY"]` ，并指定 `product` ）
各 GPU 类型的可用容量与 CUDA 版本	GPU 读取结果中的 `cudaVersions` ； `get-capacity` 用于查看矩阵视图

Shared discipline (every resource)

通用规范（所有资源）

Read first. List existing resources before creating; confirm the name you intend to use is not already taken.
Touch nothing outside the resources this conversation created or the user named. Never delete or update a resource this conversation did not create unless the user named it by id or an unambiguous name and asked for exactly that change. A user-named resource is deleted only on the user's ask for that delete. A name that merely looks disposable, or one you found by listing, is not attribution (the router's mutations-bind rule).
Confirm by read-back. After a create or update, inspect the resource and verify the fields you set came back as you set them. A write call's own response is not a read, so confirm from a fresh one. (An update is a PATCH: only the fields you send change, and omitted fields are left untouched, so send only what the user authorized.)
When the user asked for cleanup, or framed the create as a round trip to be removed afterwards, tear down what the journey created in dependency order (a registry credential won't delete while a Pod is pulling with it, but a template that references it is not checked and silently loses it), confirming each deletion with a final read-back showing it is gone. Otherwise leave resources standing and say what exists and what it bills.
State cost before creating a billable resource. A network volume bills storage per GB-month for as long as it exists. Say the size, and that it bills until deleted, before you create it. A global volume bills for stored data plus per-request fees until deleted (rates in
```
runpod-usage
```
storage
); say so before creating one. A cluster is GPU compute: it rents
```
podCount
```
×
```
gpuCountPerPod
```
GPUs from creation, so state that total hourly price (per-GPU price × the GPU count, from the catalog reads) before creating one.

先读取。 创建前先列出已有资源；确认打算使用的名称尚未被占用。
不得触碰本次对话创建或用户明确指定之外的资源。 除非用户通过 id 或无歧义名称指定某个资源，并明确要求执行相应变更，否则不得删除或更新本次对话未创建的资源。即使用户指定了某个资源，也只能在其明确要求删除时将其删除。名称看起来像是临时资源，或仅通过列出操作发现，并不能作为资源归属依据（路由器的
```
mutations-bind
```
规则）。
通过回读确认。 创建或更新后，检查资源并验证已设置字段的返回值与设置值一致。写入调用自身的响应不算作读取，因此必须通过一次新的读取进行确认。（更新操作是 PATCH：只会更改发送的字段，未发送的字段保持不变，因此只发送用户授权的字段。）
当用户要求清理，或明确表示创建流程结束后需要删除资源时，按依赖顺序拆除本次流程创建的资源（当 Pod 正在使用某个镜像仓库凭据时，该凭据无法删除；但引用该凭据的模板不会被检查，并会静默失去该引用），并通过最终回读确认每次删除均已完成。否则应保留资源，并说明当前存在哪些资源以及这些资源会产生哪些费用。
创建计费资源前说明费用。 网络卷在存续期间按 GB-月收取存储费用。创建前应说明卷大小，并说明在删除前会持续计费。全局卷在删除前会按存储数据量加每次请求费用计费（费率见
```
runpod-usage
```
storage
）；创建前应明确说明。集群属于 GPU 计算资源：从创建时起会租用
```
podCount
```
×
```
gpuCountPerPod
```
个 GPU，因此创建前应说明总小时价格（根据目录读取结果，以单 GPU 价格乘以 GPU 数量计算）。

Journeys

使用流程

Reusable template CRUD. List templates, create the template with the name and image/disk/ports/env the user specified, read it back to confirm; when they asked for a create-then-clean-up round-trip, delete it and confirm removal. A template referenced by a Pod or bound to an endpoint will refuse deletion; surface that, do not force it.
Network volume lifecycle. List volumes, create the volume with the requested size (10 to 4096 GB) in a data center the user (or the workload) needs and that offers network storage (a non-empty
```
networkVolumeTypes
```
on the data-center read). State the storage cost. Read it back and leave it to serve its purpose. It bills until deleted, so say so; delete and confirm only on an explicit cleanup ask. A volume's size may only increase; a shrink is rejected.
Volume-backed model files. Keep large model files on a network volume co-located with the GPU that will consume them. Read the data centers with their per-GPU availability (
```
include:["GPU_AVAILABILITY"]
```
) to pick a data center that has the target GPU in stock for the product you will run there, and create the volume there. Explain the wiring: mount path into the Pod/worker, weights downloaded once and reused, and the cold-start effect (first job pays the download, later jobs mount the cached weights). Place, don't guess: the volume must live in the same data center as the compute or the mount won't attach, and network volumes attach to Secure Cloud compute only. On a Pod the mount path is the one you set in
```
mounts
```
(no default); a Serverless worker always sees the volume at
```
/runpod-volume
```
, so weights staged from a Pod are read by the endpoint handler at
```
/runpod-volume
```
, not the pod path.
Cleanup asks. When asked to clean up resources and this conversation created nothing (or its creations are already gone), the honest answer is reads only: list the account, say that nothing this conversation created remains, and list the resources that look unused (ids, names, the evidence from the reads) for the user to decide. Never delete on a name-guess; that report is the complete answer.
Global volume lifecycle. List global volumes, create one with just a
```
name
```
, state the billing shape, and read it back. Attach it in the pod or endpoint create (
```
mounts.global
```
), then read it back (a pod's mount
```
path
```
; an endpoint's
```
mounts.global
```
entry, whose workers always see
```
/runpod-volume
```
).
```
update-global-volume
```
only renames. A delete is refused with
```
409
```
while any pod (stopped pods included) or endpoint still mounts it; surface that rather than terminating or detaching anything yourself. Limits, mount paths and caveats:
```
runpod-usage
```
storage
.
Account audit and organization reads. "Who deleted my endpoint?" or "who is in my organization?" are reads:
```
list-audit-logs
```
(filter by action or time window, or by actor on an organization account only, since a personal or team account gets
```
400
```
for the actor filter) and the organization reads. An account whose plan does not include audit logs gets
```
403
```
, and the organization reads return
```
404
```
when the caller is not in an organization, a team account included (
```
403
```
when organizations are unavailable to the caller); state either as the answer, not as a tool failure.
Private registry creds + pull-fail diagnosis. Create the registry credential for the private image. Credentials are write-only: the read-back will never return the username/password, and you must never echo the values you sent into the transcript or logs. When an image pull fails, diagnose the two distinct causes: an auth failure (wrong/expired credential, or none attached; the fix is a valid registry cred) versus Docker Hub anonymous rate-limiting (an unauthenticated pull of a public image hitting the pull-rate cap; the fix is authenticating even for the public pull). Name which one from the error text; do not conflate them.
Missing credential values. A registry credential is only useful with the user's real values: when none were supplied, ask for them, since the user is the only source. Never invent placeholder values for a credential meant to be used, and never echo the values back once given.
Account secret CRUD. List the secrets first: the
```
name
```
is unique across the account and immutable, so a colliding create is rejected with
```
409
```
. Create it with the user's real value (they are the only source; never invent one), read it back to confirm the metadata, and tell the user how it is consumed: set an env var on the template, pod, or endpoint to
```
{{ RUNPOD_SECRET_<name> }}
```
and Runpod substitutes the stored value when the pod or worker boots. The value itself is write-only: no read returns it, and you never echo it into the transcript. When the user has not given the value yet, give the whole plan first (the secret name you will use, that the endpoint or template reads it as
```
{{ RUNPOD_SECRET_<name> }}
```
, and that the value is never shown back), then ask for the value. Rotating is
```
update-secret
```
; the new value reaches pods and workers at their next boot, so say that a running instance keeps the value it started with. Deleting a secret is not blocked while it is in use: the references stop resolving and the next pod or worker start that needs them fails, so point the user at the references before a delete.
SSH keys on the account.
```
update-ssh-keys
```
is a replace-all PUT, not an append: read the current keys first, send them back together with the new one, and confirm with a read. Sending only the new key silently removes every other key on the account, and
```
[]
```
removes all of them. Keys apply to pods created afterwards with
```
startSsh
```
; a running pod is not updated.
Multi-node cluster lifecycle. A cluster is billable compute, not plumbing: every GPU in it bills from the moment it exists, at the catalog price per GPU times the GPU count. Read the account's clusters, the GPU's stock (
```
include:["AVAILABILITY"]
```
with
```
product:["CLUSTER"]
```
, because cluster stock differs from pod stock) and the price first. Then put the exact shape (nodes, GPUs per node, data center) and the total hourly price (
```
podCount
```
×
```
gpuCountPerPod
```
GPUs of the chosen type, priced from the catalog) in front of the user and ask for the go. Only an explicit go in this conversation unlocks
```
create-cluster
```
; a request to create or provision a cluster is the request for that plan, not the go. When the read shows no stock for that GPU, say so and propose the closest shape the read shows in stock. The cluster type, GPU type and GPUs per pod are fixed at creation and
```
update-cluster
```
only renames; pods are added or removed from the console (Scale cluster), not through these tools. So get the shape right the first time and hand a resize to the console. Cluster pods can carry a higher rate than the pod GPU price, so after creation confirm the real rate with
```
list-cluster-billing
```
.
```
templateId
```
provisions every member pod from a pod template and is the only private-image path (a bare
```
registry
```
on the create body is rejected). Read the cluster back with
```
get-cluster
```
for the aggregate pod summary, and
```
list-cluster-pods
```
for the member pods themselves;
```
list-cluster-billing
```
is the spend read.

可复用模板 CRUD。 列出模板，按照用户指定的名称、镜像、磁盘、端口和环境变量创建模板，回读以确认配置；当用户要求进行“先创建后清理”的往返流程时，删除模板并确认其已移除。被 Pod 引用或绑定到 endpoint 的模板会拒绝删除；应如实说明这一点，不要强制删除。
网络卷生命周期。 列出卷，在用户或工作负载所需且支持网络存储的数据中心中创建指定大小（10 至 4096 GB）的卷（数据中心读取结果中的
```
networkVolumeTypes
```
必须为非空）。说明存储费用。回读并进行确认，然后保留资源以发挥作用。卷会持续计费直至删除，因此应明确说明；仅在用户明确要求清理时执行删除并确认。卷的大小只能增加，缩容操作会被拒绝。
基于卷存储的模型文件。 将大型模型文件保存在与使用它们的 GPU 同址的网络卷上。读取数据中心及其每种 GPU 的可用量（
```
include:["GPU_AVAILABILITY"]
```
），选择目标 GPU 对于计划运行的产品仍有库存的数据中心，并在该处创建卷。说明连接方式：将挂载路径配置到 Pod/worker 中，权重只需下载一次即可反复使用，并解释冷启动影响（首个作业承担下载时间，后续作业直接挂载已缓存的权重）。必须实际选择位置，不能猜测：卷必须与计算资源位于同一数据中心，否则无法挂载；网络卷只能挂载到 Secure Cloud 计算资源。在 Pod 上，挂载路径是
```
mounts
```
中设置的路径（没有默认值）；Serverless worker 始终在
```
/runpod-volume
```
看到该卷，因此从 Pod 暂存的权重会由 endpoint 处理器在
```
/runpod-volume
```
读取，而不是通过 Pod 路径读取。
清理请求。 当用户要求清理资源，但本次对话未创建任何资源（或已创建的资源均已消失）时，诚实的答复只能包含读取结果：列出账户资源，说明本次对话创建的资源没有残留，并列出看起来未被使用的资源（id、名称以及读取结果中的证据），供用户决定。绝不根据名称猜测并删除资源；此时资源报告就是完整答复。
全局卷生命周期。 列出全局卷，仅使用
```
name
```
创建一个卷，说明计费方式，然后回读确认。在创建 Pod 或 endpoint 时通过
```
mounts.global
```
挂载该卷，随后回读确认（查看 Pod 挂载的
```
path
```
，或 endpoint 的
```
mounts.global
```
条目；worker 始终在
```
/runpod-volume
```
看到该卷）。
```
update-global-volume
```
只能用于重命名。只要仍有任何 Pod（包括已停止的 Pod）或 endpoint 挂载该卷，删除操作就会返回
```
409
```
；应如实说明，不要自行终止或卸载任何资源。限制、挂载路径及注意事项见
```
runpod-usage
```
storage
。
账户审计与组织读取。 “谁删除了我的 endpoint？”或“组织中有哪些成员？”属于读取操作：使用
```
list-audit-logs
```
（可按操作或时间窗口筛选；仅组织账户可按 actor 筛选，因为个人账户或团队账户使用该筛选条件会返回
```
400
```
）以及组织读取工具。如果账户套餐不包含审计日志，则返回
```
403
```
；调用者不属于任何组织时，组织读取操作返回
```
404
```
，团队账户也包括在内；当调用者无法使用组织功能时返回
```
403
```
。应将这些状态直接作为答案说明，而不是将其描述为工具故障。
私有镜像仓库凭据与拉取失败诊断。 为私有镜像创建镜像仓库凭据。凭据是只写数据：回读永远不会返回用户名或密码，且绝不能将发送的值回显到对话记录或日志中。镜像拉取失败时，应区分两种不同原因：认证失败（凭据错误或过期，或者未附加凭据；修复方式是提供有效的镜像仓库凭据）与 Docker Hub 匿名拉取限流（匿名拉取公共镜像时触发拉取频率上限；修复方式是即使拉取公共镜像也进行认证）。根据错误文本指明具体原因，不要将两者混为一谈。
缺少凭据值。 镜像仓库凭据只有使用用户的真实值才有意义：如果用户未提供这些值，应向其询问，因为用户是唯一的信息来源。绝不要为实际使用的凭据虚构占位值，并且在用户提供后绝不要回显这些值。
账户 Secret CRUD。 先列出 Secret：
```
name
```
在账户内唯一且不可变，因此名称冲突的创建请求会返回
```
409
```
。使用用户的真实值进行创建（用户是唯一的信息来源，绝不能虚构），回读以确认元数据，并告知用户其使用方式：在模板、Pod 或 endpoint 上设置环境变量
```
{{ RUNPOD_SECRET_<name> }}
```
，Runpod 会在 Pod 或 worker 启动时替换为存储的值。Secret 的值本身是只写数据：任何读取操作都不会返回该值，且绝不能将其回显到对话记录中。如果用户尚未提供值，应先给出完整方案（将使用的 Secret 名称、endpoint 或模板通过
```
{{ RUNPOD_SECRET_<name> }}
```
读取它，以及该值绝不会被回显），然后再询问具体值。轮换使用
```
update-secret
```
；新值会在 Pod 和 worker 下次启动时生效，因此应说明运行中的实例会继续使用启动时加载的值。删除 Secret 不会因正在使用而被阻止：相关引用将停止解析，下一次需要该 Secret 的 Pod 或 worker 启动时会失败，因此删除前应先向用户指出这些引用位置。
账户上的 SSH 密钥。
```
update-ssh-keys
```
是全量替换的 PUT，而不是追加操作：先读取当前密钥，再将已有密钥与新密钥一起发送，并通过读取进行确认。如果只发送新密钥，会静默移除账户上的所有其他密钥；发送
```
[]
```
则会移除全部密钥。密钥仅应用于之后通过
```
startSsh
```
创建的 Pod；运行中的 Pod 不会更新。
多节点集群生命周期。 集群属于计费计算资源，而非普通基础设施：其中的每个 GPU 从存在的那一刻起就会按目录中的单 GPU 价格计费。先读取账户的集群、GPU 库存（使用
```
include:["AVAILABILITY"]
```
并指定
```
product:["CLUSTER"]
```
，因为集群库存与 Pod 库存不同）以及价格。然后向用户展示准确的配置（节点数、每个节点的 GPU 数、数据中心）和总小时价格（根据目录价格，将所选 GPU 类型的价格乘以
```
podCount
```
×
```
gpuCountPerPod
```
个 GPU），并请求用户确认执行。只有本次对话中的明确确认才能调用
```
create-cluster
```
；要求创建或置备集群只表示需要先提供该方案，并不构成最终确认。如果读取结果显示该 GPU 没有库存，应如实说明，并提出读取结果中有库存的最接近配置。集群类型、GPU 类型以及每个 Pod 的 GPU 数量在创建时固定，
```
update-cluster
```
只能重命名；Pod 通过控制台中的 Scale cluster 增减，不能通过这些工具操作。因此首次配置必须准确，需要调整规模时交由控制台处理。集群 Pod 的费率可能高于普通 Pod 的 GPU 价格，因此创建后应使用
```
list-cluster-billing
```
确认真实费率。
```
templateId
```
会根据一个 Pod 模板置备每个成员 Pod，并且是使用私有镜像的唯一路径（创建请求体中仅设置
```
registry
```
会被拒绝）。使用
```
get-cluster
```
读取集群的 Pod 汇总信息，使用
```
list-cluster-pods
```
查看具体成员 Pod，并通过
```
list-cluster-billing
```
读取支出。

Hard rules

硬性规则

Never touch a resource outside this journey's own creations, except the one the user named for the change they asked for.
Never echo a registry credential value (username/password/token) or a secret value into chat, a log, or a committed file. Both are write-only by design; keep them that way.
Read the registered SSH keys before replacing them.
```
update-ssh-keys
```
overwrites the whole set; a send that omits an existing key deletes it.
Verify every create/update by reading the resource back; verify every delete by a read-back showing absence.
State the storage cost before creating a network or global volume and the total hourly price before creating a cluster. For a cluster, wait for the user's explicit go as well.
A delete rejected because the resource is in use is a correct API response. Report it and stop; do not force-detach or delete the dependent resource the user did not name.

绝不能触碰本次流程自身创建之外的资源，唯一例外是用户明确指定并要求变更的资源。
绝不能将镜像仓库凭据值（用户名、密码或 token）或 Secret 值回显到聊天、日志或已提交的文件中。两者均被设计为只写数据，必须保持这一特性。
替换 SSH 密钥前必须先读取已注册的密钥。
```
update-ssh-keys
```
会覆盖整个集合；如果请求中遗漏现有密钥，就会将其删除。
每次创建或更新后都要回读资源进行验证；每次删除后都要回读并确认资源已不存在。
创建网络卷或全局卷前说明存储费用，创建集群前说明总小时价格。对于集群，还必须等待用户明确确认执行。
如果删除操作因资源正在使用而被拒绝，这是正确的 API 响应。报告阻塞原因并停止；不要强行卸载或删除用户未指定的依赖资源。

Error handling

错误处理

A delete returns
```
204
```
with no body. That is success; confirm with a follow-up read.
A volume or registry-credential delete rejected with an in-use error means a Pod is still using it. Name the blocker; do not cascade. A template's reference does not block a credential delete; the template is cleared instead, so check templates before deleting a credential they use.
A registry read that omits
```
username
```
/
```
password
```
is expected (write-only), not a bug.
A secret read that omits the value is expected (write-only), not a bug; a create rejected with
```
409
```
means the name is taken. Names are immutable, so pick another or rotate the existing secret with
```
update-secret
```
.
```
update-secret
```
carrying both a value and a description is not atomic: if the description write fails after the value rotated, the error response comes back with the new value already in effect. Send the two in separate calls when that partial outcome matters.
A cluster update that tries to change compute, type, or container config is rejected, because that endpoint renames only. Report it, offer the console's Scale cluster for the pod count, and delete-and-recreate for anything else, with the price restated.

删除操作返回
```
204
```
且没有响应体。这表示成功；应通过后续读取进行确认。
如果卷或镜像仓库凭据的删除操作因正在使用而被拒绝，说明仍有 Pod 正在使用它。应指出具体阻塞项，不要级联删除。模板引用不会阻止凭据删除；相应模板会被清除，因此删除凭据前应先检查是否有模板正在使用它。
镜像仓库凭据读取结果中省略
```
username
```
/
```
password
```
属于预期行为（只写），并非故障。
Secret 读取结果中省略其值属于预期行为（只写），并非故障；创建操作返回
```
409
```
表示名称已被占用。名称不可变，因此应选择其他名称，或使用
```
update-secret
```
轮换现有 Secret。
```
update-secret
```
同时携带值和描述时并不具备原子性：如果值成功轮换后描述写入失败，错误响应返回时新值已经生效。若需要避免这种部分成功状态，应分两次调用。
集群更新操作如果尝试更改计算资源、类型或容器配置，会被拒绝，因为该端点仅用于重命名。应报告此情况，并建议通过控制台的 Scale cluster 调整 Pod 数量；其他变更需要删除后重新创建，并再次说明价格。

Report template — resource inventory

报告模板——资源清单

When asked what exists on the account (inventory, audit, "what's running"): list pods, endpoints, templates, network volumes and global volumes; a table per non-empty kind works well (name, id, status, GPU/size, $/hr where the read provides it), with empty kinds noted in a line ("templates: none"). Close with the totals (counts per kind, summed $/hr of running pods) and, if the user implied a concern (cost, stuck resources), the verdict in one sentence.

当用户询问账户中存在哪些资源（清单、审计、“当前正在运行什么”）时：列出 Pod、endpoint、模板、网络卷和全局卷；每种非空资源类型使用一个表格效果较好（名称、id、状态、GPU/大小、读取结果提供的 $/小时等信息），并用一行标注空类型（“templates: none”）。最后给出汇总（每种类型的数量，以及运行中 Pod 的 $/小时总额），如果用户表达了相关担忧（费用、资源卡住等），再用一句话给出结论。

Contract

契约

The cross-journey answer contract (definite facts from reads, commit-don't-hedge, mutations bind to this conversation's creations, a standalone final message, honest failure, granted tools only) is defined in the

runpod-mcp

skill and applies to every reply from this journey. If the

runpod-mcp

skill has not been loaded in this conversation, load it now, before the next tool call: its rules on which resources you may change, when a request is the go, and when to stop for the user are not repeated here.

跨流程回答契约（基于读取结果给出确定事实、commit-don't-hedge、变更操作绑定到本次对话创建的资源、提供独立完整的最终消息、如实报告失败、仅使用已授权工具）定义在

runpod-mcp

skill 中，并适用于本流程的每一次回复。如果本次对话尚未加载

runpod-mcp

skill，应在下次调用工具之前立即加载：其中关于哪些资源可以变更、何种请求构成执行确认，以及何时应停止并交由用户处理的规则，不会在此重复说明。