Skip to content

Update kagent and kmcp API reference docs #399

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
artberger merged 1 commit into from
Jun 27, 2026
+20 −72
Merged

Update kagent and kmcp API reference docs #399

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 13 additions & 71 deletions src/app/docs/kagent/resources/api-ref/page.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,8 +71,8 @@ Agent is the Schema for the agents API.



AgentHarness is a generic remote execution environment provisioned by a backend
(e.g. OpenShell) and addressable by exec/SSH.
AgentHarness is a generic remote execution environment provisioned by a
backend (OpenClaw or Hermes) running on Agent Substrate.



Expand All @@ -97,7 +97,7 @@ AgentHarnessBackendType selects which sandbox control plane provisions the
environment. Additional backends may be added in the future.

_Validation:_
- Enum: [openclaw nemoclaw hermes]
- Enum: [openclaw hermes]

_Appears in:_
- [AgentHarnessSpec](#agentharnessspec)
Expand All @@ -106,7 +106,6 @@ _Appears in:_
| Field | Description |
| --- | --- |
| `openclaw` | |
| `nemoclaw` | |
| `hermes` | |


Expand Down Expand Up @@ -219,27 +218,11 @@ _Appears in:_
| `homeChannelName` _string_ | HomeChannelName is a human-readable label for HomeChannel (SLACK_HOME_CHANNEL_NAME). | | |


#### AgentHarnessNetwork



AgentHarnessNetwork captures the minimal network-policy knobs exposed to users.



_Appears in:_
- [AgentHarnessSpec](#agentharnessspec)

| Field | Description | Default | Validation |
| --- | --- | --- | --- |
| `allowedDomains` _string array_ | AllowedDomains is a list of DNS names the harness may reach. | | |


#### AgentHarnessOpenClawSlackOptions



AgentHarnessOpenClawSlackOptions configures OpenClaw/NemoClaw-specific Slack routing.
AgentHarnessOpenClawSlackOptions configures OpenClaw-specific Slack routing.



Expand All @@ -253,24 +236,6 @@ _Appears in:_
| `interactiveReplies` _boolean_ | | true | |


#### AgentHarnessRuntime

_Underlying type:_ _string_

AgentHarnessRuntime selects which control plane provisions the harness VM.

_Validation:_
- Enum: [openshell substrate]

_Appears in:_
- [AgentHarnessSpec](#agentharnessspec)

| Field | Description |
| --- | --- |
| `openshell` | |
| `substrate` | |


#### AgentHarnessSlackChannelSpec


Expand All @@ -288,7 +253,7 @@ _Appears in:_
| --- | --- | --- | --- |
| `botToken` _[AgentHarnessChannelCredential](#agentharnesschannelcredential)_ | | | |
| `appToken` _[AgentHarnessChannelCredential](#agentharnesschannelcredential)_ | | | |
| `openclaw` _[AgentHarnessOpenClawSlackOptions](#agentharnessopenclawslackoptions)_ | OpenClaw configures OpenClaw/NemoClaw-specific Slack routing. | | |
| `openclaw` _[AgentHarnessOpenClawSlackOptions](#agentharnessopenclawslackoptions)_ | OpenClaw configures OpenClaw-specific Slack routing. | | |
| `hermes` _[AgentHarnessHermesSlackOptions](#agentharnesshermesslackoptions)_ | Hermes configures Hermes-specific Slack settings. | | |


Expand All @@ -311,13 +276,11 @@ _Appears in:_

| Field | Description | Default | Validation |
| --- | --- | --- | --- |
| `backend` _[AgentHarnessBackendType](#agentharnessbackendtype)_ | Backend selects the control plane to use. Required. | | Enum: [openclaw nemoclaw hermes] <br /> |
| `runtime` _[AgentHarnessRuntime](#agentharnessruntime)_ | Runtime selects the harness provisioning stack. Defaults to openshell when unset. | openshell | Enum: [openshell substrate] <br /> |
| `substrate` _[AgentHarnessSubstrateSpec](#agentharnesssubstratespec)_ | Substrate is required when runtime is substrate. | | |
| `backend` _[AgentHarnessBackendType](#agentharnessbackendtype)_ | Backend selects the control plane to use. Required. | | Enum: [openclaw hermes] <br /> |
| `substrate` _[AgentHarnessSubstrateSpec](#agentharnesssubstratespec)_ | Substrate configures the Agent Substrate provisioning stack. Required. | | |
| `description` _string_ | Description is a short human-readable summary shown in the UI (e.g. agents list). | | |
| `image` _string_ | Image is the container image to run in the harness VM, if the backend<br />supports per-resource images. Backends openclaw and nemoclaw pin the image<br />to the NemoClaw sandbox base when this field is empty; backend hermes pins<br />to the Hermes sandbox base image when empty. | | |
| `image` _string_ | Image is the container image to run in the harness VM, if the backend<br />supports per-resource images. Backend openclaw pins the image<br />to the OpenClaw sandbox base when this field is empty; backend hermes pins<br />to the Hermes sandbox base image when empty. | | |
| `env` _[EnvVar](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.31/#envvar-v1-core) array_ | Env is a list of environment variables injected into the harness workload.<br />Values use the Kubernetes EnvVar shape; ValueFrom references are<br />resolved server-side where supported. | | |
| `network` _[AgentHarnessNetwork](#agentharnessnetwork)_ | Network controls outbound access from the harness. When unset,<br />backend defaults apply. | | |
| `modelConfigRef` _string_ | ModelConfigRef is the reference to the ModelConfig used to configure the harness.<br />The controller registers the gateway provider and, after the harness is Ready,<br />writes OpenClaw config inside the VM (~/.openclaw/openclaw.json) and starts the gateway. | | |
| `channels` _[AgentHarnessChannel](#agentharnesschannel) array_ | Channels configures Telegram and Slack integrations for OpenClaw inside the harness VM. | | MaxItems: 1024 <br /> |

Expand Down Expand Up @@ -354,7 +317,7 @@ _Appears in:_

| Field | Description | Default | Validation |
| --- | --- | --- | --- |
| `backend` _[AgentHarnessBackendType](#agentharnessbackendtype)_ | | | Enum: [openclaw nemoclaw hermes] <br /> |
| `backend` _[AgentHarnessBackendType](#agentharnessbackendtype)_ | | | Enum: [openclaw hermes] <br /> |
| `id` _string_ | | | |


Expand Down Expand Up @@ -396,9 +359,7 @@ _Appears in:_
| --- | --- | --- | --- |
| `workerPoolRef` _[TypedLocalReference](#typedlocalreference)_ | WorkerPoolRef references an existing ate.dev WorkerPool in the harness namespace.<br />When unset, the controller uses its configured default WorkerPool. | | |
| `snapshotsConfig` _[AgentHarnessSubstrateSnapshotsConfig](#agentharnesssubstratesnapshotsconfig)_ | SnapshotsConfig configures actor memory snapshots. Defaults to<br />gs://ate-snapshots/&lt;namespace&gt;/&lt;agentharnessname&gt; when unset. | | |
| `workloadImage` _string_ | WorkloadImage overrides the default nemoclaw/openclaw sandbox image in the ActorTemplate. | | |
| `gatewayToken` _string_ | GatewayToken is the OpenClaw gateway Bearer token for this harness.<br />Prefer gatewayTokenSecretRef for production secrets. | | MinLength: 1 <br /> |
| `gatewayTokenSecretRef` _[TypedLocalReference](#typedlocalreference)_ | GatewayTokenSecretRef references a Secret key holding the OpenClaw gateway Bearer token.<br />The Secret must contain a "token" key. | | |
| `workloadImage` _string_ | WorkloadImage overrides the default openclaw sandbox image in the ActorTemplate. | | |


#### AgentHarnessTelegramChannelSpec
Expand Down Expand Up @@ -752,7 +713,7 @@ _Appears in:_

| Field | Description | Default | Validation |
| --- | --- | --- | --- |
| `runtime` _[DeclarativeRuntime](#declarativeruntime)_ | Runtime specifies which ADK implementation to use for this agent.<br />- "python": Uses the Python ADK (default, slower startup, full feature set)<br />- "go": Uses the Go ADK (faster startup, most features supported)<br />The runtime determines both the container image and readiness probe configuration. | python | Enum: [python go] <br /> |
| `runtime` _[DeclarativeRuntime](#declarativeruntime)_ | Runtime specifies which ADK implementation to use for this agent.<br />- "go": Uses the Go ADK (default, faster startup, most features supported)<br />- "python": Uses the Python ADK (slower startup, full feature set)<br />The runtime determines both the container image and readiness probe configuration. | go | Enum: [python go] <br /> |
| `systemMessage` _string_ | SystemMessage is a string specifying the system message for the agent.<br />When PromptTemplate is set, this field is treated as a Go text/template<br />with access to an include("source/key") function and agent context variables<br />such as .AgentName, .AgentNamespace, .Description, .ToolNames, and .SkillNames. | | |
| `systemMessageFrom` _[ValueSource](#valuesource)_ | SystemMessageFrom is a reference to a ConfigMap or Secret containing the system message.<br />When PromptTemplate is set, the resolved value is treated as a Go text/template. | | |
| `promptTemplate` _[PromptTemplateSpec](#prompttemplatespec)_ | PromptTemplate enables Go text/template processing on the systemMessage field.<br />When set, systemMessage is treated as a Go template with access to the include function<br />and agent context variables. | | |
Expand Down Expand Up @@ -1338,7 +1299,7 @@ _Appears in:_



SandboxAgent declares an agent that runs in an isolated sandbox (agent-sandbox or Agent Substrate).
SandboxAgent declares an agent that runs in an isolated sandbox on Agent Substrate.



Expand Down Expand Up @@ -1375,8 +1336,7 @@ _Appears in:_
| `skills` _[SkillForAgent](#skillforagent)_ | Skills to load into the agent. They will be pulled from the specified container images.<br />and made available to the agent under the `/skills` folder. | | |
| `sandbox` _[SandboxConfig](#sandboxconfig)_ | Sandbox configures sandboxed execution behavior shared across runtimes.<br />This is intended for sandboxed declarative execution today, and can also<br />be consumed by BYO agents. | | |
| `allowedNamespaces` _[AllowedNamespaces](#allowednamespaces)_ | AllowedNamespaces defines which namespaces are allowed to reference this Agent as a tool.<br />This follows the Gateway API pattern for cross-namespace route attachments.<br />If not specified, only Agents in the same namespace can reference this Agent as a tool.<br />This field only applies when this Agent is used as a tool by another Agent.<br />See: https://gateway-api.sigs.k8s.io/guides/multiple-ns/#cross-namespace-route-attachment | | |
| `platform` _[SandboxPlatform](#sandboxplatform)_ | Platform selects the sandbox control plane. Defaults to agent-sandbox. | agent-sandbox | Enum: [agent-sandbox substrate] <br /> |
| `substrate` _[SandboxSubstrateSpec](#sandboxsubstratespec)_ | Substrate is optional substrate-specific settings when platform is substrate. | | |
| `substrate` _[SandboxSubstrateSpec](#sandboxsubstratespec)_ | Substrate is optional Agent Substrate-specific settings. | | |


#### SandboxConfig
Expand All @@ -1396,24 +1356,6 @@ _Appears in:_
| `network` _[NetworkConfig](#networkconfig)_ | Network configures outbound network access for sandboxed execution paths.<br />When unset or when allowedDomains is empty, outbound access is denied by default. | | |


#### SandboxPlatform

_Underlying type:_ _string_

SandboxPlatform selects the control plane for sandboxed agents.

_Validation:_
- Enum: [agent-sandbox substrate]

_Appears in:_
- [SandboxAgentSpec](#sandboxagentspec)

| Field | Description |
| --- | --- |
| `agent-sandbox` | |
| `substrate` | |


#### SandboxSubstrateSpec


Expand Down
8 changes: 7 additions & 1 deletion src/app/docs/kagent/resources/helm/page.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ A Helm chart for kagent, built with Google ADK
| controller.agentImage.tag | string | `""` | |
| controller.auth.mode | string | `"unsecure"` | |
| controller.auth.userIdClaim | string | `""` | |
| controller.env | string | `nil` | |
| controller.env | list | `[]` | |
| controller.envFrom | list | `[]` | |
| controller.image.pullPolicy | string | `""` | |
| controller.image.registry | string | `""` | |
Expand All @@ -99,6 +99,7 @@ A Helm chart for kagent, built with Google ADK
| controller.resources.limits.memory | string | `"512Mi"` | |
| controller.resources.requests.cpu | string | `"100m"` | |
| controller.resources.requests.memory | string | `"128Mi"` | |
| controller.service.annotations | object | `{}` | |
| controller.service.ports.port | int | `8083` | |
| controller.service.ports.targetPort | int | `8083` | |
| controller.service.type | string | `"ClusterIP"` | |
Expand Down Expand Up @@ -313,7 +314,11 @@ A Helm chart for kagent, built with Google ADK
| ui.image.registry | string | `""` | |
| ui.image.repository | string | `"kagent-dev/kagent/ui"` | |
| ui.image.tag | string | `""` | |
| ui.nginx | object | `{"proxyReadTimeout":"1800s","proxySendTimeout":"1800s"}` | Nginx proxy timeout configuration for the UI sidecar (values are passed directly to the corresponding nginx directives, e.g. "1800s"). |
| ui.nginx.proxyReadTimeout | string | `"1800s"` | proxy_read_timeout: max time between two successive reads from the upstream. |
| ui.nginx.proxySendTimeout | string | `"1800s"` | proxy_send_timeout: max time between two successive writes to the upstream. |
| ui.nodeSelector | object | `{}` | Node labels to match for `Pod` [scheduling](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/). |
| ui.openshiftRoute.annotations."haproxy.router.openshift.io/timeout" | string | `"120m"` | |
| ui.podAnnotations | object | `{}` | |
| ui.podSecurityContext | object | (uses global podSecurityContext) | Pod-level security context for the UI pod. Overrides the global podSecurityContext. |
| ui.publicBackendUrl | string | `"/api"` | |
Expand All @@ -330,6 +335,7 @@ A Helm chart for kagent, built with Google ADK
| ui.service.ports.targetPort | int | `8080` | |
| ui.service.type | string | `"ClusterIP"` | |
| ui.startupProbe | object | httpGet /health on port http, periodSeconds=1, initialDelaySeconds=1 | Custom startup probe for the UI container. Override to adjust thresholds, use exec-based probes, or change the health path. |
| ui.streamTimeoutSeconds | int | `1800` | Client-side chat stream inactivity timeout (seconds). The browser aborts a streaming response if no event is received within this window. Should be >= ui.nginx.proxyReadTimeout so nginx isn't the silent limit. Default 1800 (30m). |
| ui.tolerations | list | `[]` | Node taints which will be tolerated for `Pod` [scheduling](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/). |
| ui.volumes | object | `{"nextjsCache":"100Mi","tmp":"50Mi"}` | EmptyDir volume sizes for Next.js UI workload (typically used when enabling readOnlyRootFilesystem) |
| ui.volumes.nextjsCache | string | `"100Mi"` | Size limit for Next.js build cache (.next/cache). Default 100Mi is sufficient for typical Next.js apps with moderate caching needs. |
Expand Down
Loading