ArkSettings

ArkSettings stores reusable prompt fragments and model settings shared across multiple ArkAgents — analogous to a Kubernetes ConfigMap.

API: arkonis.dev/v1alpha1 Kind: ArkSettings Scope: Namespaced

ArkSettings stores reusable prompt fragments and model settings that can be referenced from multiple ArkAgent resources. Define a persona or output format once and share it across many agents.

Example

apiVersion: arkonis.dev/v1alpha1
kind: ArkSettings
metadata:
  name: analyst-base
  namespace: default
spec:
  temperature: "0.3"
  outputFormat: structured-json
  memoryBackend: in-context
  promptFragments:
    persona: "You are an expert analyst."
    outputRules: "Always cite sources. Flag uncertainty explicitly."

Referencing from ArkAgent

apiVersion: arkonis.dev/v1alpha1
kind: ArkAgent
metadata:
  name: analyst-agent
spec:
  model: llama3.2
  systemPrompt: |
    Analyze the provided dataset and identify key trends.
  configRef:
    name: analyst-base

The operator resolves configRef during reconciliation, merges promptFragments into the effective system prompt, and injects temperature and outputFormat as environment variables into agent pods.

ArkSettings and the referencing ArkAgent must be in the same namespace.

Spec reference

spec

FieldTypeRequiredDescription
temperaturestringnoSampling temperature. String-encoded float (e.g. "0.7").
outputFormatstringnostructured-json, markdown, or plain.
memoryBackendstringnoin-context (default), redis, or vector-store. For durable backends, use ArkMemory instead.
promptFragmentsmap[string]stringnoNamed prompt fragments merged into the effective system prompt.

promptFragments merge order

KeyMerge position
personaPrepended to the system prompt.
outputRulesAppended after the system prompt.

Other keys are appended in alphabetical order.

See also