Function getLLMAttributes

getLLMAttributes(
    options: {
        inputMessages?: Message[];
        invocationParameters?: Record<string, unknown>;
        modelName?: string;
        outputMessages?: Message[];
        provider?: string;
        requestModelName?: string;
        responseModelName?: string;
        system?: string;
        tokenCount?: TokenCount;
        tools?: Tool[];
    },
): Attributes
Generates attributes for LLM operations.

Creates comprehensive OpenTelemetry attributes for LLM interactions including provider, model, messages, token counts, and tools.
Parameters
- options: {
      inputMessages?: Message[];
      invocationParameters?: Record<string, unknown>;
      modelName?: string;
      outputMessages?: Message[];
      provider?: string;
      requestModelName?: string;
      responseModelName?: string;
      system?: string;
      tokenCount?: TokenCount;
      tools?: Tool[];
  }
  Configuration object for LLM attributes
  - OptionalinputMessages?: Message[]
    
    Input messages sent to the LLM
  - OptionalinvocationParameters?: Record<string, unknown>
    
    Parameters used for the LLM invocation
  - OptionalmodelName?: string
    
    The name of the LLM model
  - OptionaloutputMessages?: Message[]
    
    Output messages received from the LLM
  - Optionalprovider?: string
    
    The LLM provider (e.g., "openai", "anthropic")
  - OptionalrequestModelName?: string
    
    The model requested by the caller, as sent in the request. When modelName is omitted, llm.model_name is mirrored from responseModelName ?? requestModelName
  - OptionalresponseModelName?: string
    
    The model that actually generated the response, as reported by the provider
  - Optionalsystem?: string
    
    The LLM system type
  - OptionaltokenCount?: TokenCount
    
    Token usage information
  - Optionaltools?: Tool[]
    
    Tools available to the LLM
Returns Attributes
OpenTelemetry attributes for LLM operations
Example
```
const attrs = getLLMAttributes({
  provider: "openai",
  modelName: "gpt-4",
  inputMessages: [{ role: "user", content: "Hello" }],
  outputMessages: [{ role: "assistant", content: "Hi there!" }],
  tokenCount: { prompt: 10, completion: 5, total: 15 }
});
```
- Defined in helpers/attributeHelpers.ts:656