litellm/litellm-rust/crates/cache-redis/src/script.rs
devin-ai-integration[bot] 4677f1028e
refactor(rust): align the cache crates with Python and wire every native backend (#42530)
* refactor(rust): align the cache crates with Python and activate every backend

The cache port had drifted: lifecycle and Redis-only operations sat on
`BaseCache`, counters were pinned to `f64`, each semantic backend defined its
own embedder and prompt handling, and only the in-memory backend could be
selected natively.

- Split `disconnect` and `test_connection` out of `BaseCache` into optional
  capabilities, implemented only where the Python class defines them, and give
  every Redis-only operation its own capability trait.
- Decouple counters from the stored value type, so one backend can serve both
  responses and counters as Python's `RedisCache` does.
- Share one `Embedder` and prompt contract in `litellm_cache::semantic`, and
  make the Redis and Valkey semantic backends generic over their codec.
- Port the Python operations that were missing: `async_refresh_ttl`,
  `async_rpush_and_trim`, `async_set_cache_pipeline_with_ttls`, the DualCache
  pipeline, sadd, bulk delete and TTL reads, and the semantic-similarity
  write-back.
- Take the HTTP client from the host pool in the GCS, S3 and Azure backends.
- Activate all nine backends through the Rust catalog, whose rules all stay
  `PYTHON_ONLY`, and route the `Cache` facade's storage calls to the native
  runtime when one is selected.
- Give every crate the same layout, move all tests to `tests/` on rstest, and
  add the shared `litellm-cache-testing` contract suite.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* fix: freeze native cache request kwargs and batch entries for type discipline

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

* fix: declare semantic lookup methods in the native stub

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

* refactor(rust): align the cache crates with Python and activate every backend

The cache port had drifted: lifecycle and Redis-only operations sat on
`BaseCache`, counters were pinned to `f64`, each semantic backend defined its
own embedder and prompt handling, and only the in-memory backend could be
selected natively.

- Split `disconnect` and `test_connection` out of `BaseCache` into optional
  capabilities, implemented only where the Python class defines them, and give
  every Redis-only operation its own capability trait.
- Decouple counters from the stored value type, so one backend can serve both
  responses and counters as Python's `RedisCache` does.
- Share one `Embedder` and prompt contract in `litellm_cache::semantic`, and
  make the Redis and Valkey semantic backends generic over their codec.
- Port the Python operations that were missing: `async_refresh_ttl`,
  `async_rpush_and_trim`, `async_set_cache_pipeline_with_ttls`, the DualCache
  pipeline, sadd, bulk delete and TTL reads, and the semantic-similarity
  write-back.
- Take the HTTP client from the host pool in the GCS, S3 and Azure backends.
- Activate all nine backends through the Rust catalog, whose rules all stay
  `PYTHON_ONLY`, and route the `Cache` facade's storage calls to the native
  runtime when one is selected.
- Give every crate the same layout, move all tests to `tests/` on rstest, and
  add the shared `litellm-cache-testing` contract suite.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* fix: freeze native cache request kwargs and batch entries for type discipline

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

* fix: declare semantic lookup methods in the native stub

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

* test(rust): opt the native Messages and tokenizer suites into Rust explicitly

#42517 made the Messages, token counter and tokenizer routes Python-only, so
tests/test_litellm_rust silently exercised the Python path or failed outright.
Each suite now prepends a RUST_OPT_IN rule for its route, keeping native
coverage without changing the shipped default.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(rust): pop one at a time in the Redis 6 lpop pipeline and drop explanatory comments

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

---------

Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-22 13:13:02 -07:00

136 lines
3.1 KiB
Rust

use std::sync::Arc;
use litellm_cache::{CacheCodec, CacheScript, Error, ScriptCache};
use crate::{
cache::{RedisCache, namespaced_key},
connection::Connections,
};
#[derive(Clone, Debug, PartialEq)]
pub enum RedisArg {
Bytes(Vec<u8>),
Integer(i64),
Float(f64),
}
impl From<&str> for RedisArg {
fn from(value: &str) -> Self {
Self::Bytes(value.as_bytes().to_vec())
}
}
impl From<String> for RedisArg {
fn from(value: String) -> Self {
Self::Bytes(value.into_bytes())
}
}
impl From<Vec<u8>> for RedisArg {
fn from(value: Vec<u8>) -> Self {
Self::Bytes(value)
}
}
impl From<i64> for RedisArg {
fn from(value: i64) -> Self {
Self::Integer(value)
}
}
impl From<f64> for RedisArg {
fn from(value: f64) -> Self {
Self::Float(value)
}
}
impl redis::ToRedisArgs for RedisArg {
fn write_redis_args<W>(&self, out: &mut W)
where
W: ?Sized + redis::RedisWrite,
{
match self {
Self::Bytes(value) => value.write_redis_args(out),
Self::Integer(value) => value.write_redis_args(out),
Self::Float(value) => value.write_redis_args(out),
}
}
}
pub struct RedisScript<C> {
connections: Arc<Connections<C>>,
namespace: Option<String>,
source: String,
}
impl<C> CacheScript for RedisScript<C>
where
C: redis::ConnectionLike + Send + 'static,
{
type Argument = RedisArg;
type Output = redis::Value;
async fn invoke(
&self,
keys: Vec<String>,
arguments: Vec<Self::Argument>,
) -> Result<Self::Output, Error> {
let keys = keys
.into_iter()
.map(|key| namespaced_key(self.namespace.as_deref(), &key))
.collect::<Vec<_>>();
let source = self.source.clone();
Connections::run_blocking(Arc::clone(&self.connections), move |connection| {
eval(connection, &source, keys, arguments)
})
.await
}
}
impl<S, C> RedisCache<S, C>
where
S: CacheCodec,
C: redis::ConnectionLike + Send + 'static,
{
pub async fn async_eval(
&self,
script: String,
keys: Vec<String>,
arguments: Vec<RedisArg>,
) -> Result<redis::Value, Error> {
let keys = self.namespaced_keys(&keys);
self.run(move |connection| eval(connection, &script, keys, arguments))
.await
}
}
fn eval(
connection: &mut impl redis::ConnectionLike,
script: &str,
keys: Vec<String>,
arguments: Vec<RedisArg>,
) -> Result<redis::Value, Error> {
redis::cmd("EVAL")
.arg(script)
.arg(keys.len())
.arg(keys)
.arg(arguments)
.query(connection)
.map_err(|_| Error::Unavailable)
}
impl<S, C> ScriptCache for RedisCache<S, C>
where
S: CacheCodec,
C: redis::ConnectionLike + Send + 'static,
{
type Script = RedisScript<C>;
fn async_register_script(&self, source: String) -> Self::Script {
RedisScript {
connections: Arc::clone(&self.connections),
namespace: self.namespace.clone(),
source,
}
}
}