Skip to main content

Interface: PromptEngineResult

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:222

Comprehensive result object returned by prompt construction, containing the formatted prompt, metadata, issues encountered, and optimization information. PromptEngineResult

Properties​

cacheKey?​

optional cacheKey: string

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:264

An optional cache key if the result was retrieved from or stored in a cache.

estimatedTokenCount?​

optional estimatedTokenCount: number

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:231

Estimated token count of the constructed prompt before precise provider counting.

formattedToolSchemas?​

optional formattedToolSchemas: any[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:229

Formatted tool schemas compatible with the target model's API, if tools are used. The structure of any[] depends on ModelTargetInfo.toolSupport.format.

issues?​

optional issues: object[]

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:235

Any issues (errors, warnings, info) encountered during prompt construction.

code​

code: string

component?​

optional component: string

details?​

optional details: unknown

message​

message: string

suggestion?​

optional suggestion: string

type​

type: "error" | "warning" | "info"

metadata​

metadata: object

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:254

Performance metrics and metadata related to the prompt construction process.

Index Signature​

[key: string]: unknown

constructionTimeMs​

constructionTimeMs: number

historyMessagesIncluded​

historyMessagesIncluded: number

ragContextTokensUsed?​

optional ragContextTokensUsed: number

selectedContextualElementIds​

selectedContextualElementIds: string[]

templateUsed​

templateUsed: string

totalSystemPromptsApplied​

totalSystemPromptsApplied: number

modificationDetails?​

optional modificationDetails: object

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:246

Details about modifications made during construction (e.g., which components were truncated).

addedContextualElementIds?​

optional addedContextualElementIds: string[]

originalEstimatedTokenCount?​

optional originalEstimatedTokenCount: number

removedComponents?​

optional removedComponents: string[]

summarizedComponents?​

optional summarizedComponents: string[]

truncatedComponents?​

optional truncatedComponents: string[]

prompt​

prompt: FormattedPrompt

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:224

The final formatted prompt ready for LLM consumption.

tokenCount?​

optional tokenCount: number

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:233

Precise token count, if available from a tokenizer or after construction.

wasTruncatedOrSummarized​

wasTruncatedOrSummarized: boolean

Defined in: packages/agentos/src/core/llm/IPromptEngine.ts:244

Indicates if content was truncated or summarized to fit token limits.