litellm/litellm-rust/crates/host-python/src/hooks.rs
devin-ai-integration[bot] e4190d86a6
refactor(rust): centralize host execution and compose callbacks (#43515)
* refactor(rust): extract litellm-host-native as the shared Rust host driver

Move service and hook dispatch out of host-http into a Driver that owns the
machine and Rust handlers, returning at completion or a stream boundary and
holding the demand reply until the consumer advances. Move the in-process
runner onto the same driver. host-http now layers encoding, SSE, body polling
and lifecycle observation over it. host-python keeps driving litellm-host
directly

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(rust): interrupt the machine when the in-process stream consumer fails

Restores the pre-refactor interruption path for StreamConsumer errors via
Driver::fail and ports the generic run lifecycle tests into host-native.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(rust): separate the machine contract from coroutine execution

* auth update

* refactor(rust): use standard flow control for host requests

* style(rust): keep host driver imports formatted

* chores

* mostly relocation

* refactor(rust): separate interceptors from queued observers

* refactor(rust): centralize legacy callback mappings and lifecycle

* docs: define Python host boundaries and migration plan

* refactor: enforce Python host and bridge boundaries

* refactor(rust): separate operations from callback composition

* refactor(rust): compose SDK policy through call hooks

---------

Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-28 19:20:27 +00:00

37 lines
1.1 KiB
Rust

mod chain;
pub use chain::HookChain;
use crate::PythonOwned;
use litellm_host::hooks::{CallHooks, HookRuntime, RuntimeCallEvent};
use pyo3::prelude::*;
use pyo3::types::PyDict;
/// What a hook step produced: either the value the driver asked for, or a Python
/// awaitable the driver hands back to the caller's task before asking again.
pub type HookResume<L, T> = fn(&mut L, Python<'_>, PyResult<Py<PyAny>>) -> PyResult<HookStep<L, T>>;
pub enum HookStep<L, T> {
Await(Py<PyAny>, HookResume<L, T>),
Ready(T),
}
pub struct PythonRuntime;
impl HookRuntime for PythonRuntime {
type Context<'a> = Python<'a>;
type Arguments = Py<PyDict>;
type Response = Py<PyAny>;
type Chunk = Py<PyAny>;
type Error = PyErr;
type Step<H, T> = HookStep<H, T>;
fn ready<H, T>(value: T) -> Self::Step<H, T> {
HookStep::Ready(value)
}
}
pub type PythonCallEvent<'a> = RuntimeCallEvent<'a, PythonRuntime>;
pub trait PythonCallHooks: CallHooks<PythonRuntime> + PythonOwned {}
impl<H: CallHooks<PythonRuntime> + PythonOwned> PythonCallHooks for H {}