mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-12 23:01:41 +00:00
1d5ab42e14
* 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>
28 lines
887 B
TOML
28 lines
887 B
TOML
[workspace]
|
|
members = [
|
|
"crates/core",
|
|
"crates/providers",
|
|
"crates/python-bridge",
|
|
"crates/ai-gateway",
|
|
]
|
|
resolver = "2"
|
|
|
|
[workspace.package]
|
|
edition = "2021"
|
|
license = "MIT"
|
|
repository = "https://github.com/BerriAI/litellm"
|
|
|
|
[workspace.dependencies]
|
|
litellm-core = { path = "crates/core" }
|
|
litellm-providers = { path = "crates/providers" }
|
|
axum = "0.7"
|
|
pyo3 = "0.23.5"
|
|
rand = "0.8"
|
|
reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls"] }
|
|
serde = { version = "1.0", features = ["derive"] }
|
|
serde_json = "1.0"
|
|
subtle = "2"
|
|
thiserror = "2.0"
|
|
tokio = { version = "1", features = ["rt-multi-thread", "macros", "time"] }
|
|
tokio-tungstenite = { version = "0.24", default-features = false, features = ["connect", "rustls-tls-native-roots"] }
|
|
futures-util = { version = "0.3", default-features = false, features = ["sink", "std"] }
|