build(rust): raise pyo3 to 0.29 so the native bridge compiles on Python 3.14

litellm-rust/Cargo.toml

@@ -15,8 +15,8 @@ repository = "https://github.com/BerriAI/litellm"
 litellm-core = { path = "crates/core" }
 litellm-ai-gateway = { path = "crates/ai-gateway", default-features = false }
 axum = "0.7"
-pyo3 = "0.23.5"
-pyo3-async-runtimes = { version = "0.23.0", features = ["tokio-runtime"] }
+pyo3 = "0.29.0"
+pyo3-async-runtimes = { version = "0.29.0", features = ["tokio-runtime"] }
 rand = "0.8"
 reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls", "http2", "stream"] }
 serde = { version = "1.0", features = ["derive"] }

litellm-rust/crates/ai-gateway/src/python/config.rs

@@ -17,7 +17,7 @@ use crate::gil;
 /// Load the router's `model_list` from `config_path` via the Python reader.
 pub fn load_router_from_config(config_path: &str) -> CoreResult<Router> {
     gil::record_acquisition();
-    Python::with_gil(|py| {
+    Python::attach(|py| {
         let model_list = py
             .import("litellm.proxy.read_model_list")
             .and_then(|module| module.getattr("read_model_list"))

litellm-rust/crates/python-bridge/src/gil.rs

@@ -2,7 +2,7 @@
 //!
 //! A single chokepoint for releasing the GIL around blocking work. Every
 //! blocking call in the bridge goes through [`release_gil`] instead of calling
-//! `Python::allow_threads` directly, so the release count stays accurate and we
+//! `Python::detach` directly, so the release count stays accurate and we
 //! have one place to extend later (timing histograms, per-call labels, etc.).
 
 use std::sync::atomic::{AtomicU64, Ordering};
@@ -23,7 +23,7 @@ where
     T: Send,
 {
     GIL_RELEASES.fetch_add(1, Ordering::Relaxed);
-    py.allow_threads(f)
+    py.detach(f)
 }
 
 /// Total GIL releases performed by the bridge so far.

litellm-rust/crates/python-bridge/src/lib.rs

@@ -167,7 +167,7 @@ fn aocr(
         .await
         .map_err(core_error_to_pyerr)?;
 
-        Python::with_gil(|py| json_to_py(py, value))
+        Python::attach(|py| json_to_py(py, value))
     })
 }