Struct LlmCfg 

pub struct LlmCfg {

    pub enabled: bool,
    pub api_style: String,
    pub models: BTreeMap<String, ModelPrice>,
    pub on_unpriced_model: String,
    pub budgets: Vec<BudgetCfg>,
    pub store: String,
    pub redis_url: String,
    pub redis_prefix: String,
    pub fail_open: bool,
    pub default_max_tokens: u64,
    pub team_header: String,
    pub keys: Vec<KeyEntryCfg>,
    pub dlp: DlpCfg,
    pub telemetry: TelemetryCfg,
}

LLM token-metering settings ([llm]). When enabled, the proxy parses OpenAI-compatible request/response bodies to count tokens (from the upstream’s usage object) and, for any model listed in [llm.models], the cost. Metering is observe-only: it never blocks or alters traffic. An unmapped model still has its tokens counted (cost is simply omitted).

Fields

enabled: bool

Turn on the LLM gateway: token metering, cost attribution, budgets, the key vault and DLP. Off by default, and irrelevant unless the upstream is an LLM API.

api_style: String

Wire format. Only "openai" is understood today (the default).

models: BTreeMap<String, ModelPrice>

Per-model price book, keyed by the model string clients send. Prices are USD per 1,000,000 tokens. Example: [llm.models."gpt-4o"] input_per_1m = 2.5 / output_per_1m = 10.0.

on_unpriced_model: String

What to do with a request whose model is not in [llm.models]: "count" (default — meter tokens, omit cost, forward the request) or "block" (reject 402 before it reaches the upstream, so an unpriced model is never served at a silent $0). "block" only bites when a price book is configured — a metering-only deployment (empty [llm.models]) never rejects.

budgets: Vec<BudgetCfg>

Hard token/cost budgets (gateway L1). Empty by default (no enforcement — L0 metering only). Each [[llm.budgets]] is a ceiling enforced fail-closed via reserve→reconcile. See BudgetCfg.

store: String

Budget store backend: "memory" (single replica / default) or "redis" (shared across replicas — required for a true fleet-wide cap). "local" is treated as "memory".

redis_url: String

Redis URL when store = "redis", e.g. redis://127.0.0.1:6379. Note: EDGEGUARD_REDIS_URL only overrides ratelimit.redis_url, not this key — set it here (or via pushed policy).

redis_prefix: String

Key prefix for budget keys in Redis (namespacing a shared server). Defaults to edgeguard.

fail_open: bool

On a budget-store error, allow the request (true) or reject it 503 (false, the default — fail-closed, so an outage can’t silently uncap spend).

default_max_tokens: u64

Completion tokens to assume when a request omits max_tokens, used only for the reserve estimate (the reservation is reconciled to actual usage afterward). Default 1024.

team_header: String

Request header carrying the team / tag a request is attributed to, for the per-team budget scope and team chargeback. Case-insensitive; default x-edgeguard-team. A request without it falls into the shared _none team bucket.

keys: Vec<KeyEntryCfg>

BYO-key vault + egress governance (gateway L2). Empty by default (no vault). Each [[llm.keys]] maps a client-facing virtual key to a real provider key (injected upstream, never returned to the client) plus an optional per-key model egress allowlist. When any key is configured, every proxied request must present a known virtual key. See KeyEntryCfg.

dlp: DlpCfg

Edge DLP — PII / secret detection + redaction (gateway L3). Off by default. See DlpCfg.

telemetry: TelemetryCfg

OTLP span emission (gateway L4) — SDK-free tracing to an OTel-native store. Off by default. See TelemetryCfg.

Trait Implementations

impl Clone for LlmCfg

fn clone(&self) -> LlmCfg

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LlmCfg

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

Formats the value using the given formatter.

impl Default for LlmCfg

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LlmCfg

where LlmCfg: Default,

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.