Struct LlmResponse 

pub struct LlmResponse {
    pub text: Option<String>,
    pub tool_calls: Vec<ToolCall>,
    pub tokens_used: u64,
    pub input_tokens: u64,
    pub output_tokens: u64,
    pub reasoning_tokens: u64,
    pub reasoning_content: Option<String>,
    pub stop_reason: StopReason,
}

Fields

text: Option<String>

Text the model produced (may be empty if only tool calls were made).

tool_calls: Vec<ToolCall>

Tool calls the model wants to make.

tokens_used: u64

Total tokens used (input + output + reasoning) — kept for compat.

input_tokens: u64

Input (prompt) tokens.

output_tokens: u64

Output (completion) tokens.

reasoning_tokens: u64

Reasoning/thinking tokens (DeepSeek extended thinking).

reasoning_content: Option<String>

Raw reasoning content text (DeepSeek thinking mode) — must be echoed back.

stop_reason: StopReason

Stop reason.

Trait Implementations

impl Clone for LlmResponse

fn clone(&self) -> LlmResponse

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for LlmResponse

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.