Last changed in Agentgateway v1.4.1
APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
Desired model configuration.
Provider-specific settings for Azure AI.
The version of the Azure OpenAI API to use. If unset, defaults to `v1`.
The Foundry project name, required when `resourceType` is `Foundry`. Used to construct paths: /api/projects/{projectName}/openai/v1/...
The Azure resource name used to construct the endpoint host. For OpenAI: {resourceName}.openai.azure.com For Foundry: {resourceName}.services.ai.azure.com Note: when the Azure portal "Foundry legacy" template was used, the generated resource name may end in "-resource" (e.g. "myproject-resource"); that suffix is part of the resource name as the user configured it, not part of the hostname suffix agentgateway should append.
The type of Azure endpoint. Determines the host suffix.
BaseURL overrides the provider address and base path prefix. It must use the http or https scheme. Backend policies may override the default TLS configuration. Query parameters, fragments, and user info are not supported.
Provider-specific settings for Amazon Bedrock.
Guardrail policy to use for the backend. See <https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html>. If not specified, the AWS Guardrail policy will not be used.
Identifier of the Guardrail policy to use for the backend.
Version of the Guardrail policy to use for the backend.
AWS region to use for the backend. Defaults to `us-east-1` if not specified.
Provider-specific settings for a custom provider.
Kubernetes backend that serves this provider. `backendRef` may target only a namespace-local Service or InferencePool. If unset, host and port must be set on the parent provider.
API group of the referenced resource. For example, `gateway.networking.k8s.io`. When unspecified or empty string, core API group is inferred.
Kind of the referenced resource. For example, `Service`. Defaults to "Service" when not specified.
Name of the referenced resource.
Destination port number to use for this resource. Required when the referenced resource is a Kubernetes Service.
Provider-native API formats this provider supports.
Default upstream path override for this format. If unset, agentgateway uses the default path for the format.
Provider-native API format.
Conditions for selecting this model from client requests.
Model name matched against client requests. It may be exact, a suffix wildcard such as `gpt-*`, a prefix wildcard such as `*-latest`, or `*`. When omitted, the model matches metadata.name exactly.
Gateways and listeners to which this model attaches.
Group is the group of the referent. When unspecified, "gateway.networking.k8s.io" is inferred. To set the core API group (such as for a "Service" kind referent), Group must be explicitly set to "" (empty string). Support: Core
Kind is kind of the referent. There are two kinds of parent resources with "Core" support: * Gateway (Gateway conformance profile) * Service (Mesh conformance profile, ClusterIP Services only) Support for other resources is Implementation-Specific.
Name is the name of the referent. Support: Core
Namespace of the referent. Defaults to the Route's local namespace. Cross-namespace references must be explicitly allowed, for example via ReferenceGrant. Support: Core
Port this Route targets on the parent, interpreted per parent kind (for example a Gateway listener port or Service port). Support: Extended
Name of a section within the target resource, for example a Gateway Listener name or Service port name. Empty references the entire resource. Support: Core
Policies applied to this concrete model.
Credentials used to authenticate requests to this model provider.
Explicit AWS authentication method for the model provider. When omitted, default AWS SDK credential discovery is used.
AWS STS AssumeRole settings to use before signing backend requests. Ambient AWS credentials are used as the source credentials for STS.
AWS IAM role ARN to assume.
SessionName is a custom session name (RoleSessionName) for CloudTrail and Cost & Usage Report attribution. If unset, AWS generates a random name.
SessionNameExpression is a CEL expression evaluated against each request to produce the session name (RoleSessionName), for example `jwt.sub` or `request.headers["x-team"]`. If the expression does not produce a valid session name at request time, the request is rejected.
Session tags passed to STS AssumeRole for cost attribution in the AWS Cost & Usage Report, once activated. STS allows at most 50 per role session.
CEL expression evaluated against each request to produce the tag value, for example `jwt.sub` or `request.headers["x-app"]`. Requests with invalid tag values are rejected.
Key is the tag key.
Value is a static tag value.
AWS SigV4 signing region, for example `us-east-1`. Set this when the target AWS service is in a different region than the gateway. If unset, typed AWS backends may provide this automatically; otherwise the ambient AWS region is used.
Credential source for AWS credentials, defaulting to a Kubernetes `Secret`. The default Secret resolver expects `accessKey`, `secretKey`, and optional `sessionToken` keys.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
AWS SigV4 signing service name, for example `bedrock`, `bedrock-agentcore`, or `execute-api`). If unset, typed AWS backends may provide this automatically.
Azure authentication method for the model provider.
Managed identity authentication settings.
Credential source for Azure credentials, defaulting to a Kubernetes `Secret`. The default Secret resolver expects `clientID`, `tenantID`, and `clientSecret` keys.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Workload identity authentication settings. Uses the federated token and Azure env vars projected into the data plane pod. Recommended on AKS with Workload Identity enabled.
Credentials is a list of additional credentials to inject on the backend request. Each entry resolves a Secret key and writes its value to the entry's location. `credentials` is independent of the primary `key`/`secretRef`/`passthrough` mechanism and may be set on its own or alongside it.
Where the credential is inserted on the backend request.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
SecretRef references a Kubernetes Secret holding the credential value, and optionally overrides the key read from it. Defaults to `Authorization`, matching the key convention used by the top-level `secretRef`.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Google authentication method for the model provider. When omitted, default Google credential discovery is used.
Explicit `aud` value for the ID token. Only valid with `IdToken` type. If not set, the `aud` is automatically derived from the backend hostname.
Credential source for ADC-compatible Google credential JSON, defaulting to a Kubernetes `Secret`. By default, the value is read from `credentials.json`; set `secretRef.key` to override it. When omitted, ambient credentials are used.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
The type of token to generate. To authenticate to GCP services, generally an `AccessToken` is used. To authenticate to Cloud Run, an `IdToken` is used.
Inline key to use as the value of the `Authorization` header. This option is the least secure; usage of a `Secret` is preferred.
Where backend credentials are inserted. If omitted, credentials are written to the `Authorization` header with the `Bearer ` prefix. This applies to `key`, `secretRef`, and `passthrough`. Entries in `credentials` carry their own location.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
OAuth 2.0 token exchange (RFC 8693) / jwt-bearer (RFC 7523) authentication.
RFC 8693 delegation actor token. TokenExchange grant only.
may_act claim validation mode. When omitted, may_act is not enforced.
Where to read the actor token. Actor tokens have no default source.
CEL expression that extracts the credential from the request.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
OAuth token type. Empty defaults to AccessToken. Custom absolute URI values are supported for actor tokens.
Extra form params; values are CEL expressions over the incoming request.
Audiences sent to the token endpoint.
RFC 8693 token endpoint backend.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Response cache configuration.
TTL used when the token endpoint omits expires_in. Default 300s.
Default 8192; 0 disables the cache.
Client authentication for the token endpoint. When unset, none is sent.
Client ID sent to the token endpoint.
Client authentication method. Defaults to ClientSecretBasic.
Client assertion settings. Required when method is PrivateKeyJwt.
JWS signing algorithm. Defaults to RS256.
Audience for the client assertion, typically the token endpoint URL.
JWS certificate header. Required when certificateRef is set.
PEM-encoded X.509 certificate chain, leaf first, for certificateHeader. The leaf public key should match signingKeyRef; a mismatch only logs a warning but the token endpoint will reject the assertions. Required when certificateHeader is set. The key defaults to `certificate`.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Optional JWS key ID header.
PEM-encoded RSA or EC private key; key defaults to `signingKey`.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Secret providing the `clientSecret` key by default; override via `secretRef.key`. When omitted, client_id is sent without a secret, which is only valid with ClientSecretPost.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
RFC followed by the request. Defaults to TokenExchange (RFC 8693).
Where the exchanged token is written to the backend request. Defaults to Authorization: Bearer.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
Token endpoint path; defaults to "/". Must start with "/".
RFC 8693 requested_token_type. Unlike subject/actor token types, only the built-in values may be requested; custom URIs are not supported here.
Resources sent to the token endpoint.
Scopes sent to the token endpoint.
Subject token / assertion source and type. Defaults to Authorization Bearer, AccessToken. The token type may be a built-in value or a custom absolute URI for providers that support custom token exchange profiles.
Where to read the token. CEL `expression` variant is permitted.
CEL expression that extracts the credential from the request.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
OAuth token type. Empty defaults to AccessToken. Custom absolute URI values are supported for subject tokens.
Reuses a client token already validated by another policy. Those policies may strip client credentials; passthrough adds the original token back to the backend request. Without client auth policies, this has no effect.
Credential source for the authorization value, defaulting to a Kubernetes `Secret`. By default, the value is read from the `Authorization` key; set `secretRef.key` to override it. A `Bearer ` prefix is stripped only from the default `Authorization` key.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Authorization rules that clients must satisfy to use this model.
The effect of this rule when it matches. If unspecified, defaults to `Allow`. `Require` rules are cumulative: all require rules must match.
The authorization rule to evaluate. * `Allow`: any matching allow rule allows the request. * `Require`: every require rule must match for the request to be allowed. * `Deny`: any matching deny rule denies the request. `Deny` is not recommended because expression failures fail to deny; prefer `Allow` or `Require`. If used, design expressions defensively against evaluation errors. If at least one `Allow` rule is configured, requests are denied unless at least one allow rule matches.
CEL expressions that must all evaluate to true for the rule to match.
Request and response header changes applied to provider traffic.
Header changes to apply before forwarding a request.
Add adds the given header(s) (name, value) to the request before the action. It appends to any existing values associated with the header name. Input: GET /foo HTTP/1.1 my-header: foo Config: add: - name: "my-header" value: "bar,baz" Output: GET /foo HTTP/1.1 my-header: foo,bar,baz
Name of the HTTP header, case-insensitive
Value for the HTTP header
Remove the given header(s) from the HTTP request before the action. The value of Remove is a list of HTTP header names. Note that the header names are case-insensitive (see https://datatracker.ietf.org/doc/html/rfc2616#section-4.2). Input: GET /foo HTTP/1.1 my-header1: foo my-header2: bar my-header3: baz Config: remove: ["my-header1", "my-header3"] Output: GET /foo HTTP/1.1 my-header2: bar
Set overwrites the request with the given header (name, value) before the action. Input: GET /foo HTTP/1.1 my-header: foo Config: set: - name: "my-header" value: "bar" Output: GET /foo HTTP/1.1 my-header: bar
Name of the HTTP header, case-insensitive
Value for the HTTP header
Header changes to apply before returning a response.
Add adds the given header(s) (name, value) to the request before the action. It appends to any existing values associated with the header name. Input: GET /foo HTTP/1.1 my-header: foo Config: add: - name: "my-header" value: "bar,baz" Output: GET /foo HTTP/1.1 my-header: foo,bar,baz
Name of the HTTP header, case-insensitive
Value for the HTTP header
Remove the given header(s) from the HTTP request before the action. The value of Remove is a list of HTTP header names. Note that the header names are case-insensitive (see https://datatracker.ietf.org/doc/html/rfc2616#section-4.2). Input: GET /foo HTTP/1.1 my-header1: foo my-header2: bar my-header3: baz Config: remove: ["my-header1", "my-header3"] Output: GET /foo HTTP/1.1 my-header2: bar
Set overwrites the request with the given header (name, value) before the action. Input: GET /foo HTTP/1.1 my-header: foo Config: set: - name: "my-header" value: "bar" Output: GET /foo HTTP/1.1 my-header: bar
Name of the HTTP header, case-insensitive
Value for the HTTP header
Health checking and eviction behavior for this model provider.
Settings for evicting unhealthy backends.
Number of consecutive unhealthy responses required before the backend is evicted. For example, a value of 5 means the backend must receive 5 unhealthy responses in a row before being evicted. When both consecutiveFailures and healthThreshold are set, the backend is evicted when either condition is met. When neither is set, a single unhealthy response can trigger eviction.
Base time a backend should be evicted after being marked unhealthy. Subsequent evictions use multiplicative backoff (duration * times_evicted). If all endpoints are evicted, the load balancer falls back to returning evicted endpoints rather than failing entirely. If unset, defaults to `3s`.
EWMA health score threshold, from 0 to 100. When set, a backend is evicted only if its computed health drops below this value after an unhealthy response (e.g. 50 evicts when EWMA health falls below 50%). Unlike consecutiveFailures, this sliding-window average lets a single success delay eviction. If both are set, either condition evicts; if neither, a single unhealthy response evicts.
Health score from 0 to 100 assigned to a backend when it returns from eviction. For gradual recovery, set below 100; for full recovery immediately, set 100. If unset, the backend resumes with the health it had when evicted.
CEL expression that determines whether a response indicates an unhealthy backend. When the expression evaluates to true, the backend is considered unhealthy and may be evicted. For example, to evict on 5xx responses: `response.code >= 500`. When unset, any 5xx response, or a connection failure, is treated as unhealthy. This default lowers the backend's health score but does not trigger eviction on its own.
Guardrails for requests and responses sent to this model provider.
Prompt guards to apply to requests sent by the client.
AWS Bedrock Guardrails settings for prompt guarding.
Identifier of the Guardrail policy to use for the backend.
Policies for communicating with AWS Bedrock Guardrails.
Settings for authenticating to AWS Bedrock Guardrails.
AWS authentication method for Bedrock Guardrails. Use `aws: {}` for default AWS SDK credential discovery.
AWS STS AssumeRole settings to use before signing backend requests. Ambient AWS credentials are used as the source credentials for STS.
AWS IAM role ARN to assume.
SessionName is a custom session name (RoleSessionName) for CloudTrail and Cost & Usage Report attribution. If unset, AWS generates a random name.
SessionNameExpression is a CEL expression evaluated against each request to produce the session name (RoleSessionName), for example `jwt.sub` or `request.headers["x-team"]`. If the expression does not produce a valid session name at request time, the request is rejected.
Session tags passed to STS AssumeRole for cost attribution in the AWS Cost & Usage Report, once activated. STS allows at most 50 per role session.
CEL expression evaluated against each request to produce the tag value, for example `jwt.sub` or `request.headers["x-app"]`. Requests with invalid tag values are rejected.
Key is the tag key.
Value is a static tag value.
AWS SigV4 signing region, for example `us-east-1`. Set this when the target AWS service is in a different region than the gateway. If unset, typed AWS backends may provide this automatically; otherwise the ambient AWS region is used.
Credential source for AWS credentials, defaulting to a Kubernetes `Secret`. The default Secret resolver expects `accessKey`, `secretKey`, and optional `sessionToken` keys.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
AWS SigV4 signing service name, for example `bedrock`, `bedrock-agentcore`, or `execute-api`). If unset, typed AWS backends may provide this automatically.
Inline API key to use as the value of the `Authorization` header. This option is the least secure; usage of a `Secret` is preferred.
Where API keys are inserted. Defaults to the `Authorization` header with the `Bearer ` prefix. Applies to `key` and `secretRef`.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
Credential source for the API key, defaulting to a Kubernetes `Secret`. By default, the value is read from the `Authorization` key; set `secretRef.key` to override it. A `Bearer ` prefix is stripped only from the default `Authorization` key.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Settings for managing HTTP requests to the backend
Deadline for receiving a response from the backend.
HTTP protocol version for backend connections. If unset, it is inferred: `Service` appProtocol, `HTTP2` for gRPC, the original protocol for plaintext HTTP, or `HTTP1` for HTTPS because clients often upgrade HTTPS to HTTP/2 even when the backend does not support it.
Settings for managing TCP connections to the backend
Deadline for establishing a connection to the destination.
Settings for enabling TCP keepalives on the connection.
Time between keepalive probes. If unset, this defaults to 180s.
Maximum number of keepalive probes to send before dropping the connection. If unset, this defaults to 9.
Time a connection needs to be idle before keepalive probes start being sent. If unset, this defaults to 180s.
Settings for managing TLS connections to the backend When set, TLS is originated to the backend using the system trusted CA certificates, and SNI is inferred from the destination.
Application-Layer Protocol Negotiation (`ALPN`) value to use in the TLS handshake. If not present, defaults to `["h2", "http/1.1"]`.
CA certificate `ConfigMap` to use to verify the server certificate. If unset, the system's trusted certificates are used.
Name of the referent
Originates TLS but skips verification of the backend's certificate WARNING: insecure; only use if the risks are understood Modes: * `All` disables all TLS verification * `Hostname` trusts the CA certificate but ignores hostname/SAN mismatches. Still insecure; prefer `verifySubjectAltNames` where possible.
Ordered list of key exchange groups for a TLS connection. For example: `X25519_MLKEM768,X25519`.
Enables mutual TLS to the backend using `tls.key` and `tls.crt` from the referenced credential source (defaulting to a Kubernetes `Secret`). An optional `ca.cert`, if present, verifies the server certificate, but `caCertificateRefs` takes priority. If unspecified, no client certificate is used.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Server Name Indicator (`SNI`) to use in the TLS handshake. If unset, the `SNI` is automatically set based on the destination hostname.
Subject Alternative Names (`SAN`) to verify in the server certificate. If not present, the destination hostname is automatically used.
Settings for managing tunnel connections to the backend, like `HTTPS_PROXY`
Proxy server to reach. Supported types: `Service` and `Backend`.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
AWS region where the guardrail is deployed, for example `us-west-2`).
Version of the Guardrail policy to use for the backend.
Google Model Armor settings for prompt guarding.
Google Cloud location, for example `us-central1`. Defaults to `us-central1` if not specified.
Policies for communicating with Google Model Armor.
Settings for authenticating to Google Model Armor.
Google authentication method for Model Armor. Use `gcp: {}` for default Google credential discovery.
Explicit `aud` value for the ID token. Only valid with `IdToken` type. If not set, the `aud` is automatically derived from the backend hostname.
Credential source for ADC-compatible Google credential JSON, defaulting to a Kubernetes `Secret`. By default, the value is read from `credentials.json`; set `secretRef.key` to override it. When omitted, ambient credentials are used.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
The type of token to generate. To authenticate to GCP services, generally an `AccessToken` is used. To authenticate to Cloud Run, an `IdToken` is used.
Settings for managing HTTP requests to the backend
Deadline for receiving a response from the backend.
HTTP protocol version for backend connections. If unset, it is inferred: `Service` appProtocol, `HTTP2` for gRPC, the original protocol for plaintext HTTP, or `HTTP1` for HTTPS because clients often upgrade HTTPS to HTTP/2 even when the backend does not support it.
Settings for managing TCP connections to the backend
Deadline for establishing a connection to the destination.
Settings for enabling TCP keepalives on the connection.
Time between keepalive probes. If unset, this defaults to 180s.
Maximum number of keepalive probes to send before dropping the connection. If unset, this defaults to 9.
Time a connection needs to be idle before keepalive probes start being sent. If unset, this defaults to 180s.
Settings for managing TLS connections to the backend When set, TLS is originated to the backend using the system trusted CA certificates, and SNI is inferred from the destination.
Application-Layer Protocol Negotiation (`ALPN`) value to use in the TLS handshake. If not present, defaults to `["h2", "http/1.1"]`.
CA certificate `ConfigMap` to use to verify the server certificate. If unset, the system's trusted certificates are used.
Name of the referent
Originates TLS but skips verification of the backend's certificate WARNING: insecure; only use if the risks are understood Modes: * `All` disables all TLS verification * `Hostname` trusts the CA certificate but ignores hostname/SAN mismatches. Still insecure; prefer `verifySubjectAltNames` where possible.
Ordered list of key exchange groups for a TLS connection. For example: `X25519_MLKEM768,X25519`.
Enables mutual TLS to the backend using `tls.key` and `tls.crt` from the referenced credential source (defaulting to a Kubernetes `Secret`). An optional `ca.cert`, if present, verifies the server certificate, but `caCertificateRefs` takes priority. If unspecified, no client certificate is used.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Server Name Indicator (`SNI`) to use in the TLS handshake. If unset, the `SNI` is automatically set based on the destination hostname.
Subject Alternative Names (`SAN`) to verify in the server certificate. If not present, the destination hostname is automatically used.
Settings for managing tunnel connections to the backend, like `HTTPS_PROXY`
Proxy server to reach. Supported types: `Service` and `Backend`.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Google Cloud project ID.
Template ID for Google Model Armor.
Passes prompt data through the OpenAI Moderations endpoint. See https://developers.openai.com/api/reference/resources/moderations for more information.
Moderation model to use. For example, `omni-moderation`.
Policies for communicating with OpenAI.
Settings for authenticating to OpenAI.
Inline key to use as the value of the `Authorization` header. This option is the least secure; usage of a `Secret` is preferred.
Where backend credentials are inserted. Defaults to the `Authorization` header with the `Bearer ` prefix. Applies to `key` and `secretRef`.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
Credential source for the authorization value, defaulting to a Kubernetes `Secret`. By default, the value is read from the `Authorization` key; set `secretRef.key` to override it. A `Bearer ` prefix is stripped only from the default `Authorization` key.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Settings for managing HTTP requests to the backend
Deadline for receiving a response from the backend.
HTTP protocol version for backend connections. If unset, it is inferred: `Service` appProtocol, `HTTP2` for gRPC, the original protocol for plaintext HTTP, or `HTTP1` for HTTPS because clients often upgrade HTTPS to HTTP/2 even when the backend does not support it.
Settings for managing TCP connections to the backend
Deadline for establishing a connection to the destination.
Settings for enabling TCP keepalives on the connection.
Time between keepalive probes. If unset, this defaults to 180s.
Maximum number of keepalive probes to send before dropping the connection. If unset, this defaults to 9.
Time a connection needs to be idle before keepalive probes start being sent. If unset, this defaults to 180s.
Settings for managing TLS connections to the backend When set, TLS is originated to the backend using the system trusted CA certificates, and SNI is inferred from the destination.
Application-Layer Protocol Negotiation (`ALPN`) value to use in the TLS handshake. If not present, defaults to `["h2", "http/1.1"]`.
CA certificate `ConfigMap` to use to verify the server certificate. If unset, the system's trusted certificates are used.
Name of the referent
Originates TLS but skips verification of the backend's certificate WARNING: insecure; only use if the risks are understood Modes: * `All` disables all TLS verification * `Hostname` trusts the CA certificate but ignores hostname/SAN mismatches. Still insecure; prefer `verifySubjectAltNames` where possible.
Ordered list of key exchange groups for a TLS connection. For example: `X25519_MLKEM768,X25519`.
Enables mutual TLS to the backend using `tls.key` and `tls.crt` from the referenced credential source (defaulting to a Kubernetes `Secret`). An optional `ca.cert`, if present, verifies the server certificate, but `caCertificateRefs` takes priority. If unspecified, no client certificate is used.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Server Name Indicator (`SNI`) to use in the TLS handshake. If unset, the `SNI` is automatically set based on the destination hostname.
Subject Alternative Names (`SAN`) to verify in the server certificate. If not present, the destination hostname is automatically used.
Settings for managing tunnel connections to the backend, like `HTTPS_PROXY`
Proxy server to reach. Supported types: `Service` and `Backend`.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Regular expression (regex) matching for prompt guards and data masking.
The action to take if a regex pattern is matched in a request or response. This setting applies only to request matches. `PromptguardResponse` matches are always masked by default. Defaults to `Mask`.
Built-in regex patterns to match against the request or response. Matches and built-ins are additive.
Regex patterns to match against the request or response. Matches and built-ins are additive.
Custom response message to return to the client. If not specified, defaults to `The request was rejected due to inappropriate content`.
Custom response message to return to the client. If not specified, defaults to `The request was rejected due to inappropriate content`.
Status code to return to the client. Defaults to 403.
Webhook that receives requests for prompt guarding.
Webhook server to reach. Supported types: Service and Backend.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Behavior when the webhook guardrail is unavailable or returns an error. `FailOpen` allows the request to continue. `FailClosed` (default) rejects the request.
HTTP header matches used to select the headers to forward to the webhook. Request headers are used when forwarding requests and response headers are used when forwarding responses. By default, no headers are forwarded.
Name of the HTTP header to match, case-insensitive. When names are equivalent, only the first matching entry is used
How to match against the header value: `Exact` (default) or `RegularExpression`. The regex dialect is implementation-specific
Value of the HTTP header to match
CEL-computed headers to include in webhook requests.
Prompt guards to apply to responses returned by the LLM provider.
AWS Bedrock Guardrails settings for prompt guarding.
Identifier of the Guardrail policy to use for the backend.
Policies for communicating with AWS Bedrock Guardrails.
Settings for authenticating to AWS Bedrock Guardrails.
AWS authentication method for Bedrock Guardrails. Use `aws: {}` for default AWS SDK credential discovery.
AWS STS AssumeRole settings to use before signing backend requests. Ambient AWS credentials are used as the source credentials for STS.
AWS IAM role ARN to assume.
SessionName is a custom session name (RoleSessionName) for CloudTrail and Cost & Usage Report attribution. If unset, AWS generates a random name.
SessionNameExpression is a CEL expression evaluated against each request to produce the session name (RoleSessionName), for example `jwt.sub` or `request.headers["x-team"]`. If the expression does not produce a valid session name at request time, the request is rejected.
Session tags passed to STS AssumeRole for cost attribution in the AWS Cost & Usage Report, once activated. STS allows at most 50 per role session.
CEL expression evaluated against each request to produce the tag value, for example `jwt.sub` or `request.headers["x-app"]`. Requests with invalid tag values are rejected.
Key is the tag key.
Value is a static tag value.
AWS SigV4 signing region, for example `us-east-1`. Set this when the target AWS service is in a different region than the gateway. If unset, typed AWS backends may provide this automatically; otherwise the ambient AWS region is used.
Credential source for AWS credentials, defaulting to a Kubernetes `Secret`. The default Secret resolver expects `accessKey`, `secretKey`, and optional `sessionToken` keys.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
AWS SigV4 signing service name, for example `bedrock`, `bedrock-agentcore`, or `execute-api`). If unset, typed AWS backends may provide this automatically.
Inline API key to use as the value of the `Authorization` header. This option is the least secure; usage of a `Secret` is preferred.
Where API keys are inserted. Defaults to the `Authorization` header with the `Bearer ` prefix. Applies to `key` and `secretRef`.
Name of an HTTP header. HTTP/2 pseudo-headers (names beginning with `:`) are not supported
Credential source for the API key, defaulting to a Kubernetes `Secret`. By default, the value is read from the `Authorization` key; set `secretRef.key` to override it. A `Bearer ` prefix is stripped only from the default `Authorization` key.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Settings for managing HTTP requests to the backend
Deadline for receiving a response from the backend.
HTTP protocol version for backend connections. If unset, it is inferred: `Service` appProtocol, `HTTP2` for gRPC, the original protocol for plaintext HTTP, or `HTTP1` for HTTPS because clients often upgrade HTTPS to HTTP/2 even when the backend does not support it.
Settings for managing TCP connections to the backend
Deadline for establishing a connection to the destination.
Settings for enabling TCP keepalives on the connection.
Time between keepalive probes. If unset, this defaults to 180s.
Maximum number of keepalive probes to send before dropping the connection. If unset, this defaults to 9.
Time a connection needs to be idle before keepalive probes start being sent. If unset, this defaults to 180s.
Settings for managing TLS connections to the backend When set, TLS is originated to the backend using the system trusted CA certificates, and SNI is inferred from the destination.
Application-Layer Protocol Negotiation (`ALPN`) value to use in the TLS handshake. If not present, defaults to `["h2", "http/1.1"]`.
CA certificate `ConfigMap` to use to verify the server certificate. If unset, the system's trusted certificates are used.
Name of the referent
Originates TLS but skips verification of the backend's certificate WARNING: insecure; only use if the risks are understood Modes: * `All` disables all TLS verification * `Hostname` trusts the CA certificate but ignores hostname/SAN mismatches. Still insecure; prefer `verifySubjectAltNames` where possible.
Ordered list of key exchange groups for a TLS connection. For example: `X25519_MLKEM768,X25519`.
Enables mutual TLS to the backend using `tls.key` and `tls.crt` from the referenced credential source (defaulting to a Kubernetes `Secret`). An optional `ca.cert`, if present, verifies the server certificate, but `caCertificateRefs` takes priority. If unspecified, no client certificate is used.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Server Name Indicator (`SNI`) to use in the TLS handshake. If unset, the `SNI` is automatically set based on the destination hostname.
Subject Alternative Names (`SAN`) to verify in the server certificate. If not present, the destination hostname is automatically used.
Settings for managing tunnel connections to the backend, like `HTTPS_PROXY`
Proxy server to reach. Supported types: `Service` and `Backend`.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
AWS region where the guardrail is deployed, for example `us-west-2`).
Version of the Guardrail policy to use for the backend.
Google Model Armor settings for prompt guarding.
Google Cloud location, for example `us-central1`. Defaults to `us-central1` if not specified.
Policies for communicating with Google Model Armor.
Settings for authenticating to Google Model Armor.
Google authentication method for Model Armor. Use `gcp: {}` for default Google credential discovery.
Explicit `aud` value for the ID token. Only valid with `IdToken` type. If not set, the `aud` is automatically derived from the backend hostname.
Credential source for ADC-compatible Google credential JSON, defaulting to a Kubernetes `Secret`. By default, the value is read from `credentials.json`; set `secretRef.key` to override it. When omitted, ambient credentials are used.
API group of the referenced credential; empty selects the core API group
Key in the referenced Secret. If omitted, a location-specific default is used
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
The type of token to generate. To authenticate to GCP services, generally an `AccessToken` is used. To authenticate to Cloud Run, an `IdToken` is used.
Settings for managing HTTP requests to the backend
Deadline for receiving a response from the backend.
HTTP protocol version for backend connections. If unset, it is inferred: `Service` appProtocol, `HTTP2` for gRPC, the original protocol for plaintext HTTP, or `HTTP1` for HTTPS because clients often upgrade HTTPS to HTTP/2 even when the backend does not support it.
Settings for managing TCP connections to the backend
Deadline for establishing a connection to the destination.
Settings for enabling TCP keepalives on the connection.
Time between keepalive probes. If unset, this defaults to 180s.
Maximum number of keepalive probes to send before dropping the connection. If unset, this defaults to 9.
Time a connection needs to be idle before keepalive probes start being sent. If unset, this defaults to 180s.
Settings for managing TLS connections to the backend When set, TLS is originated to the backend using the system trusted CA certificates, and SNI is inferred from the destination.
Application-Layer Protocol Negotiation (`ALPN`) value to use in the TLS handshake. If not present, defaults to `["h2", "http/1.1"]`.
CA certificate `ConfigMap` to use to verify the server certificate. If unset, the system's trusted certificates are used.
Name of the referent
Originates TLS but skips verification of the backend's certificate WARNING: insecure; only use if the risks are understood Modes: * `All` disables all TLS verification * `Hostname` trusts the CA certificate but ignores hostname/SAN mismatches. Still insecure; prefer `verifySubjectAltNames` where possible.
Ordered list of key exchange groups for a TLS connection. For example: `X25519_MLKEM768,X25519`.
Enables mutual TLS to the backend using `tls.key` and `tls.crt` from the referenced credential source (defaulting to a Kubernetes `Secret`). An optional `ca.cert`, if present, verifies the server certificate, but `caCertificateRefs` takes priority. If unspecified, no client certificate is used.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Server Name Indicator (`SNI`) to use in the TLS handshake. If unset, the `SNI` is automatically set based on the destination hostname.
Subject Alternative Names (`SAN`) to verify in the server certificate. If not present, the destination hostname is automatically used.
Settings for managing tunnel connections to the backend, like `HTTPS_PROXY`
Proxy server to reach. Supported types: `Service` and `Backend`.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Google Cloud project ID.
Template ID for Google Model Armor.
Regular expression (regex) matching for prompt guards and data masking.
The action to take if a regex pattern is matched in a request or response. This setting applies only to request matches. `PromptguardResponse` matches are always masked by default. Defaults to `Mask`.
Built-in regex patterns to match against the request or response. Matches and built-ins are additive.
Regex patterns to match against the request or response. Matches and built-ins are additive.
Custom response message to return to the client. If not specified, defaults to `The response was rejected due to inappropriate content`.
Custom response message to return to the client. If not specified, defaults to `The request was rejected due to inappropriate content`.
Status code to return to the client. Defaults to 403.
Webhook that receives responses for prompt guarding.
Webhook server to reach. Supported types: Service and Backend.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Behavior when the webhook guardrail is unavailable or returns an error. `FailOpen` allows the request to continue. `FailClosed` (default) rejects the request.
HTTP header matches used to select the headers to forward to the webhook. Request headers are used when forwarding requests and response headers are used when forwarding responses. By default, no headers are forwarded.
Name of the HTTP header to match, case-insensitive. When names are equivalent, only the first matching entry is used
How to match against the header value: `Exact` (default) or `RegularExpression`. The regex dialect is implementation-specific
Value of the HTTP header to match
CEL-computed headers to include in webhook requests.
Apply prompt guards to streaming responses and realtime websocket messages. Defaults to disabled to preserve streaming throughput unless explicitly enabled.
TLS settings for connections to this model provider.
Application-Layer Protocol Negotiation (`ALPN`) value to use in the TLS handshake. If not present, defaults to `["h2", "http/1.1"]`.
CA certificate `ConfigMap` to use to verify the server certificate. If unset, the system's trusted certificates are used.
Name of the referent
Originates TLS but skips verification of the backend's certificate WARNING: insecure; only use if the risks are understood Modes: * `All` disables all TLS verification * `Hostname` trusts the CA certificate but ignores hostname/SAN mismatches. Still insecure; prefer `verifySubjectAltNames` where possible.
Ordered list of key exchange groups for a TLS connection. For example: `X25519_MLKEM768,X25519`.
Enables mutual TLS to the backend using `tls.key` and `tls.crt` from the referenced credential source (defaulting to a Kubernetes `Secret`). An optional `ca.cert`, if present, verifies the server certificate, but `caCertificateRefs` takes priority. If unspecified, no client certificate is used.
API group of the referenced credential; empty selects the core API group
Kind of the referenced credential; empty defaults to `Secret`
Name of the referenced credential
Server Name Indicator (`SNI`) to use in the TLS handshake. If unset, the `SNI` is automatically set based on the destination hostname.
Subject Alternative Names (`SAN`) to verify in the server certificate. If not present, the destination hostname is automatically used.
CEL transformations applied to fields in the provider request body.
CEL expression used to compute the field value.
Name of the field to set.
Proxy tunnel used to reach this model provider.
Proxy server to reach. Supported types: `Service` and `Backend`.
Group of the referent, for example `gateway.networking.k8s.io`. Empty selects the core API group
Kubernetes resource kind of the referent, for example `Service`. Defaults to `Service`
Name is the name of the referent.
Namespace of the referent. Defaults to the local namespace. A cross-namespace reference requires a ReferenceGrant in the referent namespace
Destination port number. Required when the referent is a Kubernetes `Service`
Provider serving this concrete model. Provider-specific configuration is set by the corresponding field below when needed.
Provider-specific settings for Vertex AI.
The ID of the Google Cloud Project that you use for the Vertex AI.
The location of the Google Cloud Project that you use for the Vertex AI. Special values: `global` uses the global endpoint, while `us` and `eu` use restricted multi-region endpoints. Other values are treated as regional locations. Defaults to `global` if not specified.
Request-time routing among concrete AgentgatewayModel resources.
Ordered condition-based model selection.
Concrete model targets evaluated in order. The first matching condition is selected. One final target may omit when to act as the fallback.
Concrete model name selected through the referenced model. It is required when modelRef points to a wildcard match.model. When omitted, the referenced model's exact effective match.model is used.
Same-namespace AgentgatewayModel resource selected by this target.
Name of the referent
CEL expression that must evaluate to true for this target to be selected. Omit only on the final fallback target.
Priority-based model selection with failover between priority groups.
Concrete model targets grouped by priority. Lower values are preferred.
Concrete model name selected through the referenced model. It is required when modelRef points to a wildcard match.model. When omitted, the referenced model's exact effective match.model is used.
Same-namespace AgentgatewayModel resource selected by this target.
Name of the referent
Priority of this target. Lower values are preferred. Targets at the same priority are selected using a score that considers health and latency. The next priority is used only when every target at this priority is degraded. Configure policies.health on concrete target models to customize degradation and eviction behavior.
Weight-based model selection.
Concrete model targets and their relative weights.
Concrete model name selected through the referenced model. It is required when modelRef points to a wildcard match.model. When omitted, the referenced model's exact effective match.model is used.
Same-namespace AgentgatewayModel resource selected by this target.
Name of the referent
Relative traffic weight. Defaults to 1.
Controls whether clients can request this model directly. Internal models can only be selected by virtual models. Defaults to Public.
Current model attachment status.
Status for each Gateway parent to which this model is attached.
Conditions describes the status of the route with respect to the Gateway. Note that the route's availability is also subject to the Gateway's own status conditions and listener status. If the Route's ParentRef specifies an existing Gateway that supports Routes of this kind AND that Gateway's controller has sufficient access, then that Gateway's controller MUST set the "Accepted" condition on the Route, to indicate whether the route has been accepted or rejected by the Gateway, and why. A Route MUST be considered "Accepted" if at least one of the Route's rules is implemented by the Gateway. There are a number of cases where the "Accepted" condition may not be set due to lack of controller visibility, that includes when: * The Route refers to a nonexistent parent. * The Route is of a type that the controller does not support. * The Route is in a namespace to which the controller does not have access. <gateway:util:excludeFromCRD> Notes for implementors: Conditions are a listType `map`, which means that they function like a map with a key of the `type` field _in the k8s apiserver_. This means that implementations must obey some rules when updating this section. * Implementations MUST perform a read-modify-write cycle on this field before modifying it. That is, when modifying this field, implementations must be confident they have fetched the most recent version of this field, and ensure that changes they make are on that recent version. * Implementations MUST NOT remove or reorder Conditions that they are not directly responsible for. For example, if an implementation sees a Condition with type `special.io/SomeField`, it MUST NOT remove, change or update that Condition. * Implementations MUST always _merge_ changes into Conditions of the same Type, rather than creating more than one Condition of the same Type. * Implementations MUST always update the `observedGeneration` field of the Condition to the `metadata.generation` of the Gateway at the time of update creation. * If the `observedGeneration` of a Condition is _greater than_ the value the implementation knows about, then it MUST NOT perform the update on that Condition, but must wait for a future reconciliation and status update. (The assumption is that the implementation's copy of the object is stale and an update will be re-triggered if relevant.) </gateway:util:excludeFromCRD>
lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable.
message is a human readable message indicating details about the transition. This may be an empty string.
observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance.
reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty.
status of the condition, one of True, False, Unknown.
type of condition in CamelCase or in foo.example.com/CamelCase.
ControllerName is a domain/path string that indicates the name of the controller that wrote this status. This corresponds with the controllerName field on GatewayClass. Example: "example.net/gateway-controller". The format of this field is DOMAIN "/" PATH, where DOMAIN and PATH are valid Kubernetes names (https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names). Controllers MUST populate this field when writing status. Controllers should ensure that entries to status populated with their ControllerName are cleaned up when they are no longer necessary.
ParentRef corresponds with a ParentRef in the spec that this RouteParentStatus struct describes the status of.
Group is the group of the referent. When unspecified, "gateway.networking.k8s.io" is inferred. To set the core API group (such as for a "Service" kind referent), Group must be explicitly set to "" (empty string). Support: Core
Kind is kind of the referent. There are two kinds of parent resources with "Core" support: * Gateway (Gateway conformance profile) * Service (Mesh conformance profile, ClusterIP Services only) Support for other resources is Implementation-Specific.
Name is the name of the referent. Support: Core
Namespace of the referent. Defaults to the Route's local namespace. Cross-namespace references must be explicitly allowed, for example via ReferenceGrant. Support: Core
Port this Route targets on the parent, interpreted per parent kind (for example a Gateway listener port or Service port). Support: Extended
Name of a section within the target resource, for example a Gateway Listener name or Service port name. Empty references the entire resource. Support: Core
Source: agentgateway.dev_agentgatewaymodels.yaml
Changes to AgentgatewayModel (agentgateway.dev/v1alpha1) in each Agentgateway version, compared to the version before it.
2 properties have been added
Released · View AgentgatewayModel in v1.4.1
AgentgatewayModel was first seen on this version of Agentgateway
Released · View AgentgatewayModel in v1.4.0
No examples of AgentgatewayModel yet. Contribute one on GitHub.
kubespec.dev