apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-18 13:45:15 +02:00
Code Issues Projects Releases Packages Wiki Activity

rename x-session-id to x-routing-session-id and fix routing config field name

Browse source
This commit is contained in:
Adil Hafeez 2026-04-08 12:31:57 -07:00
parent f699cfb059
commit 5789694d2f
11 changed files with 41 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

6
crates/brightstaff/src/handlers/llm/mod.rs
View file

@ -1,6 +1,8 @@
use bytes::Bytes;
use common::configuration::{FilterPipeline, ModelAlias};
use common::consts::{ARCH_IS_STREAMING_HEADER, ARCH_PROVIDER_HINT_HEADER, SESSION_ID_HEADER};
use common::consts::{
ARCH_IS_STREAMING_HEADER, ARCH_PROVIDER_HINT_HEADER, ROUTING_SESSION_ID_HEADER,
};
use common::llm_providers::LlmProviders;
use hermesllm::apis::openai::Message;
use hermesllm::apis::openai_responses::InputParam;
@ -96,7 +98,7 @@ async fn llm_chat_inner(
// Session pinning: extract session ID and check cache before routing
let session_id: Option<String> = request_headers
.get(SESSION_ID_HEADER)
.get(ROUTING_SESSION_ID_HEADER)
.and_then(|h| h.to_str().ok())
.map(|s| s.to_string());
let pinned_model: Option<String> = if let Some(ref sid) = session_id {

4
crates/brightstaff/src/handlers/routing_service.rs
View file

@ -1,6 +1,6 @@
use bytes::Bytes;
use common::configuration::{SpanAttributes, TopLevelRoutingPreference};
use common::consts::{REQUEST_ID_HEADER, SESSION_ID_HEADER};
use common::consts::{REQUEST_ID_HEADER, ROUTING_SESSION_ID_HEADER};
use common::errors::BrightStaffError;
use hermesllm::clients::SupportedAPIsFromClient;
use hermesllm::ProviderRequestType;
@ -72,7 +72,7 @@ pub async fn routing_decision(
.unwrap_or_else(|| uuid::Uuid::new_v4().to_string());
let session_id: Option<String> = request_headers
.get(SESSION_ID_HEADER)
.get(ROUTING_SESSION_ID_HEADER)
.and_then(|h| h.to_str().ok())
.map(|s| s.to_string());

5
crates/brightstaff/src/router/llm.rs
View file

@ -20,6 +20,7 @@ use crate::router::router_model_v1;
const DEFAULT_SESSION_TTL_SECONDS: u64 = 600;
const DEFAULT_SESSION_MAX_ENTRIES: usize = 10_000;
const MAX_SESSION_MAX_ENTRIES: usize = 10_000;
#[derive(Clone, Debug)]
pub struct CachedRoute {
@ -92,7 +93,9 @@ impl RouterService {
let session_ttl =
Duration::from_secs(session_ttl_seconds.unwrap_or(DEFAULT_SESSION_TTL_SECONDS));
let session_max_entries = session_max_entries.unwrap_or(DEFAULT_SESSION_MAX_ENTRIES);
let session_max_entries = session_max_entries
.unwrap_or(DEFAULT_SESSION_MAX_ENTRIES)
.min(MAX_SESSION_MAX_ENTRIES);
RouterService {
router_url,

2
crates/common/src/configuration.rs
View file

@ -9,7 +9,7 @@ use crate::api::open_ai::{
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Routing {
pub model_provider: Option<String>,
pub llm_provider: Option<String>,
pub model: Option<String>,
pub session_ttl_seconds: Option<u64>,
pub session_max_entries: Option<usize>,

2
crates/common/src/consts.rs
View file

@ -22,7 +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 ROUTING_SESSION_ID_HEADER: &str = "x-routing-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";