plano/crates/common/src/consts.rs

pub const RATELIMIT_SELECTOR_HEADER_KEY: &str = "x-arch-ratelimit-selector";
pub const SYSTEM_ROLE: &str = "system";
pub const USER_ROLE: &str = "user";
pub const TOOL_ROLE: &str = "tool";
pub const ASSISTANT_ROLE: &str = "assistant";
pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const DEFAULT_TARGET_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const API_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const MODEL_SERVER_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const MODEL_SERVER_NAME: &str = "bright_staff";
pub const ARCH_ROUTING_HEADER: &str = "x-arch-llm-provider";
pub const MESSAGES_KEY: &str = "messages";
pub const ARCH_PROVIDER_HINT_HEADER: &str = "x-arch-llm-provider-hint";
pub const ARCH_IS_STREAMING_HEADER: &str = "x-arch-streaming-request";
pub const CHAT_COMPLETIONS_PATH: &str = "/v1/chat/completions";
pub const MESSAGES_PATH: &str = "/v1/messages";
pub const HEALTHZ_PATH: &str = "/healthz";
pub const X_ARCH_STATE_HEADER: &str = "x-arch-state";
pub const X_ARCH_API_RESPONSE: &str = "x-arch-api-response-message";
pub const X_ARCH_TOOL_CALL: &str = "x-arch-tool-call-message";
pub const X_ARCH_FC_MODEL_RESPONSE: &str = "x-arch-fc-model-response";
pub const ARCH_FC_MODEL_NAME: &str = "Arch-Function";
pub const REQUEST_ID_HEADER: &str = "x-request-id";
pub const TRACE_PARENT_HEADER: &str = "traceparent";
pub const ARCH_INTERNAL_CLUSTER_NAME: &str = "arch_internal";
pub const ARCH_UPSTREAM_HOST_HEADER: &str = "x-arch-upstream";
pub const ARCH_MODEL_PREFIX: &str = "Arch";
pub const HALLUCINATION_TEMPLATE: &str =
    "It seems I'm missing some information. Could you provide the following details ";
pub const OTEL_COLLECTOR_HTTP: &str = "opentelemetry_collector_http";
pub const OTEL_POST_PATH: &str = "/v1/traces";
pub const LLM_ROUTE_HEADER: &str = "x-arch-llm-route";
pub const ENVOY_RETRY_HEADER: &str = "x-envoy-max-retries";