Constructor Detail

• FakePromptRunner

  FakePromptRunner(LlmOptions llm, List<Message> messages, List<AgentImage> images, Set<ToolGroupRequirement> toolGroups, List<ToolObject> toolObjects, List<PromptContributor> promptContributors, List<ContextualPromptElement> contextualPromptContributors, Boolean generateExamples, Predicate<String> propertyFilter, Boolean validation, OperationContext context, List<LlmInvocation> _llmInvocations, List<Object> responses, List<Tool> otherTools, InteractionId interactionId, List<GuardRail> guardRails)

Method Detail

• getLlmInvocations

   final List<LlmInvocation> getLlmInvocations()

• getLlm

   LlmOptions getLlm()

• getMessages

   List<Message> getMessages()

  Messages added to this PromptRunner

• getImages

   List<AgentImage> getImages()

  Images added to this PromptRunner

• getToolGroups

   Set<ToolGroupRequirement> getToolGroups()

  Tool groups exposed. This will include directly registered tool groups and tool groups resolved from ToolGroups.

• getToolObjects

   List<ToolObject> getToolObjects()

  Additional objects with @Tool annotation for use in this PromptRunner

• getPromptContributors

   List<PromptContributor> getPromptContributors()

• getGenerateExamples

   Boolean getGenerateExamples()

  Whether to generate examples for the prompt. Defaults to unknown: Set to false if generating your own examples.

• getPropertyFilter

   Predicate<String> getPropertyFilter()

  Filter that determines which properties to include when creating objects.

• getValidation

   Boolean getValidation()

  Whether to validate generated objects. Defaults to true; set to false to skip validation.

• getInteractionId

   final InteractionId getInteractionId()

  The interaction ID set via withInteractionId() or withId(). Can be inspected in tests to verify the correct ID was set.

• withInteractionId

   PromptRunner withInteractionId(InteractionId interactionId)

  Set an interaction id for this prompt runner.

• withMessages

   PromptRunner withMessages(List<Message> messages)

• withImages

   PromptRunner withImages(List<AgentImage> images)

• expectResponse

   final Unit expectResponse(Object response)

  Add a response to the list of expected responses. This is used to simulate responses from the LLM.

• createObject

   <T extends Any> T createObject(String prompt, Class<T> outputClass)

  Create an object of the given type using the given prompt and LLM options from context (process context or implementing class). Prompts are typically created within the scope of an

• createObject

   <T extends Any> T createObject(List<Message> messages, Class<T> outputClass)

  Create an object from messages

• createObjectIfPossible

   <T extends Any> T createObjectIfPossible(List<Message> messages, Class<T> outputClass)

• evaluateCondition

   Boolean evaluateCondition(String condition, String context, Double confidenceThreshold)

• withLlm

   PromptRunner withLlm(LlmOptions llm)

  Specify an LLM for the PromptRunner

• withToolGroup

   PromptRunner withToolGroup(ToolGroupRequirement toolGroup)

• withToolGroup

   PromptRunner withToolGroup(ToolGroup toolGroup)

  Allows for dynamic tool groups to be added to the PromptRunner.

• withToolObject

   PromptRunner withToolObject(ToolObject toolObject)

  Add a tool object

  Parameters:

  toolObject - the object to add.

• withPromptContributors

   PromptRunner withPromptContributors(List<PromptContributor> promptContributors)

• withContextualPromptContributors

   PromptRunner withContextualPromptContributors(List<ContextualPromptElement> contextualPromptContributors)

  Add a prompt contributor that can see context

• withGenerateExamples

   PromptRunner withGenerateExamples(Boolean generateExamples)

  Set whether to generate examples of the output in the prompt on a per-PromptRunner basis. This overrides platform defaults. Note that adding individual examples with Creating.withExample will always override this.

• withPropertyFilter

  @Deprecated(message = "Use creating().withPropertyFilter() instead") PromptRunner withPropertyFilter(Predicate<String> filter)

  Adds a filter that determines which properties are to be included when creating an object.

  Note that each predicate is applied in addition to previously registered predicates.

  Parameters:

  filter - the property predicate to be added

• withValidation

  @Deprecated(message = "Use creating().withValidation() instead") PromptRunner withValidation(Boolean validation)

  Set whether to validate created objects.

  Parameters:

  validation - true to validate created objects; false otherwise.

• rendering

   PromptRunner.Rendering rendering(String templateName)

  Returns Rendering for rendering the specified template.

  Parameters:

  templateName - the name of the template to render

  Returns:

  rendering mode for creating objects and generating text from templates

• withTool

   PromptRunner withTool(Tool tool)

  Add a framework-agnostic Tool to the prompt runner.

  Parameters:

  tool - the tool to add

  Returns:

  PromptRunner instance with the added tool

• creating

   <T extends Any> PromptRunner.Creating<T> creating(Class<T> outputClass)

  Returns a mode for creating strongly-typed objects.

  Parameters:

  outputClass - the class of objects to create

  Returns:

  creating mode supporting examples, property filtering, and validation

• withGuardRails

   PromptRunner withGuardRails(GuardRail guards)

  Add guardrail instances to this PromptRunner (additive).

  Parameters:

  guards - the guardrail instances to add

  Returns:

  PromptRunner instance with additional guardrails configured

• withToolChainingFrom

   <T extends Any> PromptRunner withToolChainingFrom(Class<T> type, DomainToolPredicate<T> predicate)

  Register a domain class with a predicate to control when its @LlmTool methods become available as tools.

  When a single artifact of the specified type is returned, any @LlmTool annotated methods on that instance become available as tools, provided the predicate is satisfied.

  When multiple artifacts of the same type are returned, "last wins" - only the most recent artifact that passes the predicate will have its tools exposed.

  Parameters:

  type - The domain class that may contribute @LlmTool methods

  predicate - Predicate to filter which instances contribute tools

• withToolChainingFromAny

   PromptRunner withToolChainingFromAny()

  Enable auto-discovery of chained tools from any returned artifact.

  When enabled, any artifact with @LlmTool methods will automatically have its tools exposed, replacing ALL previous bindings.