Skip to main content

Interface: PromptComponents

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:119

Core components that form the foundation of any prompt construction. These are gathered from various sources (GMI state, user input, RAG) and then augmented with dynamically selected contextual elements.

Interface​

PromptComponents

Properties​

assembledMemoryContext?​

optional assembledMemoryContext: AssembledMemoryContext

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:153

Assembled cognitive memory context (personality-affected, token-budgeted). Merged with retrievedContext by the prompt template.

audioInput?​

optional audioInput: AudioInputData

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:140

Audio input data references if the model or a pre-processing step handles audio.

conversationHistory?​

optional conversationHistory: ConversationMessage[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:123

Conversation history messages, typically an array of Message objects.

currentTurnMessageCount?​

optional currentTurnMessageCount: number

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:134

How many messages at the end of conversationHistory belong to the turn being answered: the current user message when it travels as history (structured input), then the assistant tool calls and tool results of the turn's earlier calls. Token budgeting summarizes or truncates only the messages before them, so the model always receives the request it answers and its own tool rounds. A tool round the first of them belongs to is kept whole with them: a call before them whose result they hold is not dropped. Defaults to 0.

customComponents?​

optional customComponents: Record<string, unknown>

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:157

Additional custom components that templates might use.

retrievedContext?​

optional retrievedContext: string | object[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:149

Retrieved context from a RAG system, to be incorporated into the prompt.

systemPrompts?​

optional systemPrompts: object[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:121

System-level prompts with optional priority ordering. Higher priority usually means placed earlier or given more weight.

content​

content: string

priority?​

optional priority: number

source?​

optional source: string

taskSpecificData?​

optional taskSpecificData: Record<string, unknown>

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:155

Task-specific data or parameters that need to be included in the prompt.

tools?​

optional tools: ITool<any, any>[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:142

Available tools and their schemas, for models that support function/tool calling.

toolSchemas?​

optional toolSchemas: Record<string, unknown>[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:147

Pre-formatted tool/function schemas that should be forwarded to the model as-is. Useful when upstream logic has already normalized the schema definitions.

userInput?​

optional userInput: string | null

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:136

Current user input text.

visionInputs?​

optional visionInputs: VisionInputData[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:138

Visual inputs (images) if the target model supports vision.