support session pinning for consistent model selection in routing (#813)

This commit is contained in:
Adil Hafeez 2026-03-13 17:32:32 -07:00
parent 785bf7e021
commit 46a5bfd82d
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
8 changed files with 406 additions and 3 deletions

View file

@ -11,6 +11,8 @@ use crate::api::open_ai::{
pub struct Routing {
pub model_provider: Option<String>,
pub model: Option<String>,
pub session_ttl_seconds: Option<u64>,
pub session_max_entries: Option<usize>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]

View file

@ -22,6 +22,7 @@ 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 SESSION_ID_HEADER: &str = "x-session-id";
pub const ENVOY_ORIGINAL_PATH_HEADER: &str = "x-envoy-original-path";
pub const TRACE_PARENT_HEADER: &str = "traceparent";
pub const ARCH_INTERNAL_CLUSTER_NAME: &str = "arch_internal";