Enum EvalLlmBackend 

pub enum EvalLlmBackend {
    Stub,
    Anthropic,
    Openai,
    Ollama,
    LlamaGuard,
}

Which model backend produced the agent response. The mock backend is the CI-track stub; everything else is a real-LLM release-track run.

Variants

Stub

Deterministic mock (scripts/eval/mock_llm.py — lands in M11.1). Returns canonical refuse / comply_safe / comply_unsafe per attack class. Fast, free, runs every PR.

Anthropic

Anthropic API. Use for the canonical pass/fail vs. spec thresholds. Default model: claude-sonnet-4-6.

Openai

OpenAI API.

Ollama

Local Ollama. Useful for gating without an API key but not the canonical baseline.

LlamaGuard

Llama-Guard-3-8B running locally via Ollama. Used as the nightly judge: grades each response as safe / unsafe.

Trait Implementations

impl Clone for EvalLlmBackend

fn clone(&self) -> EvalLlmBackend

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EvalLlmBackend

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EvalLlmBackend

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for EvalLlmBackend

fn eq(&self, other: &EvalLlmBackend) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for EvalLlmBackend

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for EvalLlmBackend

impl Eq for EvalLlmBackend

impl StructuralPartialEq for EvalLlmBackend