Model affinity for consistent model selection in agentic loops (#827)
Some checks are pending
CI / pre-commit (push) Waiting to run
CI / plano-tools-tests (push) Waiting to run
CI / native-smoke-test (push) Waiting to run
CI / docker-build (push) Waiting to run
CI / validate-config (push) Waiting to run
CI / security-scan (push) Blocked by required conditions
CI / test-prompt-gateway (push) Blocked by required conditions
CI / test-model-alias-routing (push) Blocked by required conditions
CI / test-responses-api-with-state (push) Blocked by required conditions
CI / e2e-plano-tests (3.10) (push) Blocked by required conditions
CI / e2e-plano-tests (3.11) (push) Blocked by required conditions
CI / e2e-plano-tests (3.12) (push) Blocked by required conditions
CI / e2e-plano-tests (3.13) (push) Blocked by required conditions
CI / e2e-plano-tests (3.14) (push) Blocked by required conditions
CI / e2e-demo-preference (push) Blocked by required conditions
CI / e2e-demo-currency (push) Blocked by required conditions
Publish docker image (latest) / build-arm64 (push) Waiting to run
Publish docker image (latest) / build-amd64 (push) Waiting to run
Publish docker image (latest) / create-manifest (push) Blocked by required conditions
Build and Deploy Documentation / build (push) Waiting to run

This commit is contained in:
Adil Hafeez 2026-04-08 17:32:02 -07:00 committed by GitHub
parent 978b1ea722
commit 8dedf0bec1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 614 additions and 43 deletions

View file

@ -7,6 +7,14 @@ use crate::api::open_ai::{
ChatCompletionTool, FunctionDefinition, FunctionParameter, FunctionParameters, ParameterType,
};
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Routing {
pub llm_provider: Option<String>,
pub model: Option<String>,
pub session_ttl_seconds: Option<u64>,
pub session_max_entries: Option<usize>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ModelAlias {
pub target: String,
@ -182,6 +190,7 @@ pub struct Configuration {
pub model_providers: Vec<LlmProvider>,
pub model_aliases: Option<HashMap<String, ModelAlias>>,
pub overrides: Option<Overrides>,
pub routing: Option<Routing>,
pub system_prompt: Option<String>,
pub prompt_guards: Option<PromptGuards>,
pub prompt_targets: Option<Vec<PromptTarget>>,

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 MODEL_AFFINITY_HEADER: &str = "x-model-affinity";
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";