litellm/litellm-rust/crates/cache-response/tests/codec.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

110 lines
4 KiB
Rust

use litellm_cache::{CacheCodec, Error};
use litellm_cache_response::{CacheEntry, ResponseCacheCodec};
use rstest::rstest;
use serde_json::{Value, json};
fn entry(response: Value) -> CacheEntry {
CacheEntry {
timestamp: Some(100.0),
response,
}
}
#[rstest]
#[case::python_literal_object(
br#"{'timestamp': 100.0, 'response': {'text': 'hello \\ world', 'flag': True, 'empty': None, 'list': [1, 2.5]}}"#.as_slice(),
json!({"text": "hello \\ world", "flag": true, "empty": null, "list": [1, 2.5]}),
)]
#[case::python_sync_string_response(
br#"{'timestamp': 100.0, 'response': '{"ok": true, "text": "cached"}'}"#.as_slice(),
json!({"ok": true, "text": "cached"}),
)]
#[case::python_literal_string_response(
br#"{'timestamp': 100.0, 'response': "{'ok': True, 'items': (1, 2)}"}"#.as_slice(),
json!({"ok": true, "items": [1, 2]}),
)]
#[case::json_object_response(
br#"{"timestamp":100.0,"response":{"ok":true,"text":"cached"}}"#.as_slice(),
json!({"ok": true, "text": "cached"}),
)]
#[case::json_string_response(
br#"{"timestamp": 100.0, "response": "[1,2]"}"#.as_slice(),
json!([1, 2]),
)]
fn decode_reads_every_python_envelope(#[case] bytes: &[u8], #[case] response: Value) {
assert_eq!(ResponseCacheCodec.decode(bytes).unwrap(), entry(response));
}
#[rstest]
#[case::code_is_not_executed(b"__import__('os').system('false')".to_vec())]
#[case::non_numeric_timestamp(b"{'timestamp': 'invalid', 'response': {}}".to_vec())]
#[case::infinite_timestamp(b"{'timestamp': 1e9999, 'response': {}}".to_vec())]
#[case::missing_response(br#"{"timestamp": 100.0}"#.to_vec())]
#[case::unserialized_string_response(br#"{"timestamp": 100.0, "response": "not serialized"}"#.to_vec())]
#[case::non_utf8(vec![0xff, 0xfe])]
#[case::deep_nesting(format!("{}None{}", "[".repeat(1000), "]".repeat(1000)).into_bytes())]
fn decode_rejects_invalid_entries(#[case] bytes: Vec<u8>) {
assert_eq!(
ResponseCacheCodec.decode(&bytes).unwrap_err(),
Error::InvalidEntry
);
}
#[rstest]
#[case::nan(f64::NAN)]
#[case::infinity(f64::INFINITY)]
fn encode_rejects_non_finite_timestamps(#[case] timestamp: f64) {
assert_eq!(
ResponseCacheCodec
.encode(&CacheEntry {
timestamp: Some(timestamp),
response: json!({}),
})
.unwrap_err(),
Error::InvalidEntry
);
}
#[rstest]
#[case::object(json!({"choices": [{"text": "cached"}]}), json!({"choices": [{"text": "cached"}]}))]
#[case::array(json!([1, 2]), json!("[1,2]"))]
#[case::number(json!(7), json!("7"))]
#[case::null(json!(null), json!("null"))]
#[case::string(json!("hello world"), json!("\"hello world\""))]
#[case::numeric_string(json!("123"), json!("\"123\""))]
#[case::null_string(json!("null"), json!("\"null\""))]
fn encode_writes_python_readable_envelopes_that_round_trip(
#[case] response: Value,
#[case] wire_response: Value,
) {
let wire = ResponseCacheCodec.encode(&entry(response.clone())).unwrap();
assert_eq!(
serde_json::from_slice::<Value>(&wire).unwrap(),
json!({"timestamp": 100.0, "response": wire_response})
);
assert_eq!(ResponseCacheCodec.decode(&wire).unwrap(), entry(response));
}
#[rstest]
fn object_entries_preserve_the_existing_json_representation() {
let entry = CacheEntry {
timestamp: Some(123.0),
response: json!({"choices": [{"text": "cached"}]}),
};
let bytes = ResponseCacheCodec.encode(&entry).unwrap();
assert_eq!(bytes, serde_json::to_vec(&entry).unwrap());
assert_eq!(ResponseCacheCodec.decode(&bytes).unwrap(), entry);
}
#[rstest]
#[case::json(br#"{"choices": [{"text": "legacy"}]}"#.as_slice())]
#[case::python_literal(br#"{'choices': [{'text': 'legacy'}]}"#.as_slice())]
fn values_without_timestamps_decode_as_bare_responses(#[case] bytes: &[u8]) {
assert_eq!(
ResponseCacheCodec.decode(bytes).unwrap(),
CacheEntry {
timestamp: None,
response: json!({"choices": [{"text": "legacy"}]}),
}
);
}