Struct LlmQuery 

pub struct LlmQuery {
    pub id: QueryId,
    pub prompt: String,
    pub system: Option<String>,
    pub max_tokens: u32,
    pub grounded: bool,
    pub underspecified: bool,
    pub cache_breakpoint: Option<String>,
    pub role: Option<String>,
}

LLM request emitted during execution. Transport-agnostic (no channel, HTTP, or MCP Sampling details).

Fields

id: QueryId

prompt: String

system: Option<String>

max_tokens: u32

grounded: bool

When true, the host should ground the response in external evidence (web search, code reading, documentation, etc.) rather than relying solely on LLM internal knowledge. The host decides the means.

underspecified: bool

When true, the prompt’s preconditions depend on intent/goal definitions that exist outside the current context and cannot be inferred by the LLM. The host decides the resolution means (user query, RAG, DB lookup, delegated agent, etc.).

cache_breakpoint: Option<String>

Optional opaque hint to the host on where to place a prompt-cache boundary (e.g. Anthropic cache_control block). The engine does not interpret the value — it forwards it verbatim on the paused-session JSON so the host can map it to the provider-specific cache API.

Recommended values (host-defined; engine is opaque):

• "context" — cache everything up to and including the system prompt / long shared context so that repeated calls (panel / moa / ucb) hit the cache
• "prompt" — cache the full prompt including user turn

Absent when not set; hosts that do not implement prompt caching MUST ignore the field.

role: Option<String>

Optional role hint identifying the caller context of this query.

Set to "grader" by the LLM-as-Judge grader wiring (see alc.eval) so the host can distinguish a judge/grading call from the default strategy call and route it to a different model (named model role + default fallback). The engine does not interpret the value — it forwards it verbatim on the paused-session JSON.

Absent when not set; hosts that do not implement role-based routing MUST ignore the field.

Trait Implementations

impl Clone for LlmQuery

fn clone(&self) -> LlmQuery

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LlmQuery

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for LlmQuery

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LlmQuery

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.