litellm/litellm-rust/crates/cache/src/base_cache.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

125 lines
3 KiB
Rust

use std::{future::Future, time::Duration};
use serde::{Deserialize, Serialize};
use crate::Error;
#[derive(Clone, Debug, PartialEq)]
pub enum BatchEntry<V> {
Hit(V),
Miss,
Invalid,
}
pub trait CacheContext: Clone + Send + Sync + 'static {
fn ttl(&self) -> Option<Duration>;
fn with_ttl(&self, ttl: Option<Duration>) -> Self;
}
#[derive(Clone, Debug, Default, PartialEq, Eq)]
pub struct ExactCacheContext {
pub ttl: Option<Duration>,
}
impl CacheContext for ExactCacheContext {
fn ttl(&self) -> Option<Duration> {
self.ttl
}
fn with_ttl(&self, ttl: Option<Duration>) -> Self {
Self { ttl }
}
}
#[derive(Clone, Debug, Default, PartialEq)]
pub struct SemanticCacheContext {
pub input: Option<serde_json::Value>,
pub messages: Option<serde_json::Value>,
pub metadata: Option<serde_json::Value>,
pub scope: Option<String>,
pub ttl: Option<Duration>,
}
impl CacheContext for SemanticCacheContext {
fn ttl(&self) -> Option<Duration> {
self.ttl
}
fn with_ttl(&self, ttl: Option<Duration>) -> Self {
Self {
ttl,
..self.clone()
}
}
}
#[derive(Clone, Copy, Debug, Deserialize, Serialize, PartialEq, Eq)]
#[serde(rename_all = "lowercase")]
pub enum CacheConnectionStatus {
Success,
Failed,
}
#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq)]
pub struct CacheConnectionResult {
pub status: CacheConnectionStatus,
pub message: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub error: Option<String>,
}
pub trait BaseCache: Send + Sync {
type Value: Clone + Send + Sync + 'static;
type Context: CacheContext;
fn get_ttl(&self, context: &Self::Context) -> Option<Duration>;
fn set_cache(
&self,
key: &str,
value: Self::Value,
context: &Self::Context,
) -> Result<(), Error>;
fn get_cache(&self, key: &str, context: &Self::Context) -> Result<Option<Self::Value>, Error>;
fn async_set_cache(
&self,
key: &str,
value: Self::Value,
context: Self::Context,
) -> impl Future<Output = Result<(), Error>> + Send {
async move { self.set_cache(key, value, &context) }
}
fn async_get_cache(
&self,
key: &str,
context: &Self::Context,
) -> impl Future<Output = Result<Option<Self::Value>, Error>> + Send {
async move { self.get_cache(key, context) }
}
fn async_set_cache_pipeline(
&self,
entries: Vec<(String, Self::Value)>,
context: Self::Context,
) -> impl Future<Output = Result<(), Error>> + Send {
async move {
for (key, value) in entries {
self.async_set_cache(&key, value, context.clone()).await?;
}
Ok(())
}
}
fn batch_cache_write(
&self,
key: &str,
value: Self::Value,
context: Self::Context,
) -> impl Future<Output = Result<(), Error>> + Send {
self.async_set_cache(key, value, context)
}
}