Skip to search

ModelConfig

kagent.dev / v1alpha2

apiVersion: kagent.dev/v1alpha2 kind: ModelConfig metadata: name: example
View raw schema
apiVersion string
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 string
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
metadata object
spec object
ModelConfigSpec defines the desired state of ModelConfig.
anthropic object
Anthropic-specific configuration
baseUrl string
Base URL for the Anthropic API (overrides default)
maxTokens integer
Maximum tokens to generate
temperature string
Temperature for sampling
topK integer
Top-k sampling parameter
topP string
Top-p sampling parameter
anthropicVertexAI object
Anthropic-specific configuration
location string required
The project location
maxTokens integer
Maximum tokens to generate
projectID string required
The project ID
stopSequences []string
Stop sequences
temperature string
Temperature
topK string
Top-k sampling parameter
topP string
Top-p sampling parameter
apiKeyPassthrough boolean
APIKeyPassthrough enables forwarding the Bearer token from incoming A2A requests directly to the LLM provider as the API key. This is useful for organizations with federated identity that want to avoid separate secret management. Mutually exclusive with apiKeySecret.
apiKeySecret string
The name of the secret that contains the API key. Must be a reference to the name of a secret in the same namespace as the referencing ModelConfig. For the SAPAICore provider, the secret must contain two keys: "client_id" and "client_secret" (the OAuth2 client credentials for SAP AI Core). The apiKeySecretKey field is not used for SAPAICore.
apiKeySecretKey string
The key in the secret that contains the API key. Not used for the SAPAICore provider (which always reads "client_id" and "client_secret" from the secret).
azureOpenAI object
Azure OpenAI-specific configuration
apiVersion string required
API version for the Azure OpenAI API
azureAdToken string
Azure AD token for authentication
azureDeployment string
Deployment name for the Azure OpenAI API
azureEndpoint string required
Endpoint for the Azure OpenAI API
maxTokens integer
Maximum tokens to generate
temperature string
Temperature for sampling
topP string
Top-p sampling parameter
bedrock object
AWS Bedrock-specific configuration
additionalModelRequestFields object
AdditionalModelRequestFields passes model-specific parameters to Bedrock's additionalModelRequestFields in the Converse API. Use this for provider-specific options that are not part of the standard InferenceConfiguration block, such as Claude extended thinking or top_k. Values are forwarded as-is to the API. Example: {"top_k": 5, "thinking": {"type": "enabled", "budget_tokens": 16000}}
cacheTTL string
CacheTTL controls how long Bedrock retains a cached prefix when PromptCaching is enabled. Only meaningful when PromptCaching is true. - "5m" (default): Bedrock's standard 5-minute sliding cache. Each cache hit refreshes the window. Supported by all prompt-caching models. - "1h": extended-TTL caching, useful for tasks whose Converse calls are spaced more than 5 minutes apart. NOTE: "1h" is NOT strictly better than "5m". Extended-TTL cache writes are billed at a higher per-token rate than 5-minute writes, and 1h is supported on a narrower set of models. Only choose "1h" when calls are spaced far enough apart that a 5-minute cache would expire between them; otherwise the higher write cost is wasted. See the AWS prompt-caching docs above.
enum: 5m, 1h
promptCaching boolean
PromptCaching enables Bedrock prompt caching by appending a CachePoint block at the end of the Converse request's `system` content array and the end of the `toolConfig.tools` array. Bedrock will cache the prefix up to and including those cache points across requests in the same region for roughly 5 minutes after first use, billing the cached portion at a reduced rate on cache hits. Recommended for tool-using agents that make many Converse calls per task with a stable system prompt and tool set — the per-call input token count can drop by 70-90% on hit. Has no effect on models that don't support caching; the marker is ignored by Bedrock for those. See https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html for the current list of supported models and minimum prefix sizes.
region string required
AWS region where the Bedrock model is available (e.g., us-east-1, us-west-2)
defaultHeaders object
gemini object
Gemini-specific configuration
geminiVertexAI object
Gemini Vertex AI-specific configuration
candidateCount integer
Candidate count
location string required
The project location
maxOutputTokens integer
Maximum output tokens
projectID string required
The project ID
responseMimeType string
Response mime type
stopSequences []string
Stop sequences
temperature string
Temperature
topK string
Top-k sampling parameter
topP string
Top-p sampling parameter
model string required
ollama object
Ollama-specific configuration
host string
Host for the Ollama API
options object
Options for the Ollama API
openAI object
OpenAI-specific configuration
baseUrl string
Base URL for the OpenAI API (overrides default)
frequencyPenalty string
Frequency penalty
maxTokens integer
Maximum tokens to generate
n integer
N value
organization string
Organization ID for the OpenAI API
presencePenalty string
Presence penalty
reasoningEffort string
Reasoning effort
enum: minimal, low, medium, high
seed integer
Seed value
temperature string
Temperature for sampling
timeout integer
Timeout
tokenExchange object
TokenExchange configures dynamic bearer token acquisition via credential exchange. Requires apiKeySecret (used as the service account secret) and is mutually exclusive with apiKeyPassthrough.
gdchServiceAccount object
GDCHServiceAccountConfig holds GDCH-specific token exchange parameters.
audience string required
Audience is the token exchange audience URL (the GDC inference gateway base URL)
type string required
TokenExchangeType identifies the token exchange mechanism
enum: GDCHServiceAccount
topP string
Top-p sampling parameter
provider string
The provider of the model
enum: Anthropic, OpenAI, AzureOpenAI, Ollama, Gemini, GeminiVertexAI, AnthropicVertexAI, Bedrock, SAPAICore
sapAICore object
SAP AI Core-specific configuration
authUrl string
OAuth2 token endpoint URL (e.g., https://tenant.authentication.eu10.hana.ondemand.com)
baseUrl string required
Base URL for the SAP AI Core API (e.g., https://api.ai.prod.eu-central-1.aws.ml.hana.ondemand.com)
resourceGroup string
Resource group in SAP AI Core
tls object
TLS configuration for provider connections. Enables agents to connect to internal LiteLLM gateways or other providers that use self-signed certificates or custom certificate authorities.
caCertSecretKey string
CACertSecretKey is the key within the Secret that contains the CA certificate data (PEM-encoded). Required when CACertSecretRef is set — admission rejects ref-without-key regardless of DisableVerify (see the TLSConfig-level XValidation rules).
caCertSecretRef string
CACertSecretRef is a reference to a Kubernetes Secret containing CA certificate(s) in PEM format. The Secret must be in the same namespace as the resource referencing it (ModelConfig, RemoteMCPServer, or any future consumer of TLSConfig). When set, the certificate will be used to verify the upstream's SSL certificate.
disableSystemCAs boolean
DisableSystemCAs disables the use of system CA certificates. When false (default), system CA certificates are used for verification (safe behavior). When true, only the custom CA from CACertSecretRef is trusted. This allows strict security policies where only corporate CAs should be trusted.
disableVerify boolean
DisableVerify disables SSL certificate verification entirely. When false (default), SSL certificates are verified. When true, SSL certificate verification is disabled. WARNING: This should ONLY be used in development/testing environments. Production deployments MUST use proper certificates.
status object
ModelConfigStatus defines the observed state of ModelConfig.
conditions []object
lastTransitionTime string required
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.
format: date-time
message string required
message is a human readable message indicating details about the transition. This may be an empty string.
maxLength: 32768
observedGeneration integer
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.
format: int64
minimum: 0
reason string required
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.
pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
minLength: 1
maxLength: 1024
status string required
status of the condition, one of True, False, Unknown.
enum: True, False, Unknown
type string required
type of condition in CamelCase or in foo.example.com/CamelCase.
pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
maxLength: 316
observedGeneration integer
format: int64
secretHash string
The secret hash stores a hash of any secrets required by the model config (i.e. api key, tls cert) to ensure agents referencing this model config detect changes to these secrets and restart if necessary.

No matches. Try .spec.anthropic for an exact path