litellm/litellm-rust/crates/ai-gateway/AGENTS.md
ishaan-berri 1d5ab42e14
feat: add minimal rust router + axum ai-gateway calling router.realtime (2/2) (#31135)
* add CoreError::Routing variant for deployment selection failures

* add minimal Rust Router (simple-shuffle) mirroring router.py spec

* add litellm-router crate manifest

* add ai-gateway POST /v1/realtime handler calling router.realtime

* add ai-gateway health routes

* wire ai-gateway routes into the axum app

* add ai-gateway AppState holding the shared router

* add ai-gateway axum server entrypoint

* add litellm-ai-gateway binary crate manifest

* docs: add ai-gateway folder-architecture AGENTS.md

* register router + ai-gateway crates and axum/rand deps in workspace

* update Cargo.lock for router + ai-gateway crates

* split router: extract model_list types into deployment module

* split router: extract routing policy into strategy module

* split router: move Router orchestration into router module

* router lib: wire submodules and re-export public API

* add read_model_list helper reusing ProxyConfig env/secret resolution

* add GIL-activity tracker (records acquisitions, 30s window)

* add GET /health/gil endpoint for polling GIL activity

* add pyo3 load_router_from_config bridge (feature-gated, load-time only)

* register /health/gil route in ai-gateway

* wire build_router: load from python config when feature enabled

* add optional pyo3 dep + python-config feature to ai-gateway

* update Cargo.lock for optional pyo3 dependency

* fix: satisfy strict ruff budget (FA100) in read_model_list

* test: cover read_model_list env resolution + empty config

* ai-gateway: bind localhost by default, warn on bad PORT/missing keys, wire gateway key

* ai-gateway: add gateway_key to AppState for realtime auth

* ai-gateway: require bearer auth + map unknown model to 404 on /v1/realtime

* ai-gateway: move python interop into python/ with load-time-only AGENTS.md

* ai-gateway: document auth, gil, and python folder in AGENTS.md

* core: add router module (model_list types + simple-shuffle selection)

* ai-gateway: dispatch realtime via core router + providers (drop router crate dep)

* update Cargo.lock: fold router into core

* workspace: drop crates/router member and litellm-router dep

* read_model_list: reuse ProxyConfig.get_config (includes + os.environ + DB) instead of thin yaml read

* ai-gateway: constant-time bearer compare + 500 (not 503) for unconfigured key

* ai-gateway: trim stored gateway key to match trimmed bearer token

* ai-gateway: add subtle dep for constant-time comparison

* workspace: add subtle dependency

* update Cargo.lock for subtle

* core router: make strategy a folder (one module per strategy, simple_shuffle)

* providers: make realtime() a streaming splice (client stream <-> OpenAI) instead of collect

* providers: add futures-channel dev-dep for the streaming live test

* ai-gateway: make /v1/realtime a WebSocket (auth before upgrade, splice typed events)

* ai-gateway: dispatch realtime as a stream splice

* ai-gateway: route /v1/realtime via GET (WebSocket), drop POST

* ai-gateway: enable axum ws feature + futures-util

* update Cargo.lock for ws feature + futures-channel

* core router: add has_deployment() for pre-flight model checks

* ai-gateway: extract auth into auth/ module (single master key, LITELLM_MASTER_KEY)

* ai-gateway routes: adopt router()-per-module template + merge in app()

* ai-gateway: document auth/ + routes template in AGENTS.md

* ai-gateway: realtime route as thin handler + service + transport

* ai-gateway: auth as a RequireMasterKey extractor (idiomatic axum FromRequestParts)

* ai-gateway: docs for auth extractor + simplified route template

* ai-gateway: collapse realtime route to mod.rs + service.rs; docs for extractor/template

* providers realtime: enforce idle timeout around the splice (reap stalled sessions)

* ai-gateway: rename realtime service timeout param to idle_timeout

---------

Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
2026-06-23 19:16:34 -07:00

2.7 KiB

ai-gateway — folder architecture

The Axum server that fronts the Rust gateway. It owns transport + config + auth only; deployment selection lives in core::router, transforms in core/providers.

src/
  main.rs            # entrypoint: build AppState (router + master key), bind, serve
  state.rs           # AppState — shared Arc<Router> + master_key
  gil.rs             # GIL-activity tracker (records Python acquisitions)
  auth/              # authentication as an axum extractor — added to handler args
    mod.rs           #   RequireMasterKey: FromRequestParts, single master key (LITELLM_MASTER_KEY)
  routes/            # one module per route, all matching the same template
    AGENTS.md        #   ← the route template (read this before adding a route)
    mod.rs           #   app(): merges every module's router()
    health.rs        #   simple route (one file): router() + liveness/readiness
    gil.rs           #   simple route (one file): router() + GET /health/gil
    realtime/        #   route with logic → axum surface + a no-axum service:
      mod.rs         #     router() + handler + WS<->events adapter (the axum surface)
      service.rs     #     business logic (select deployment, call provider) — no axum, testable
  python/            # Python interop (feature: python-config) — load-time only
    mod.rs, config.rs, AGENTS.md

Rules

  • Routes follow one template. Each route module exposes pub fn router() -> Router<AppState>; routes/mod.rs only merges them. Simple routes are one file; non-trivial routes are a folder (handler/service/ transport). See routes/AGENTS.md.
  • Auth is an extractor. Add crate::auth::RequireMasterKey to a handler's args; it runs during extraction. Never re-implement the check per route.
  • Handlers are thin. A handler validates and delegates to its service. No business logic, no provider calls, no transforms in handlers.
  • State is shared and cheap to clone. Long-lived handles live behind Arc in state.rs; read env/config only in main.rs when building state.

Auth (interim)

A single master key (LITELLM_MASTER_KEY), enforced by the auth::RequireMasterKey extractor: any caller presenting it as Authorization: Bearer <key> may invoke the gateway. Fails closed (500) when unset; constant-time compare. The server binds 127.0.0.1 by default (HOST to override). Full per-key auth + budgets/rate-limits are delegated to the Python proxy in a later phase. Health routes don't add the extractor (unauthenticated).

Python interop

Anything that calls into Python lives in python/ and is load-time only — see python/AGENTS.md. The realtime data path never takes the GIL.