devin-ai-integration[bot] 571ada0b0f feat(rust_bridge): mark native streams with the x-litellm-rust header (#42758) ... Non-streaming responses served by the Rust core already carry x-litellm-rust: true through _hidden_params.additional_headers, which the SDK exposes and the gateway renders as a response header. Native streams did not, because the lifecycle Stream and SyncStream objects had nowhere to hold hidden params and the marker writer skips objects without them. Give both stream classes the same _hidden_params bag every other litellm response has, so the existing marker attaches without wrapping the stream or changing its identity. Co-authored-by: Yujong Lee <yujong@berri.ai>		2026-09-24 09:36:25 -07:00
..
messages	feat(rust_bridge): mark native streams with the x-litellm-rust header (#42758)	2026-09-24 09:36:25 -07:00
ocr	test(rust): model the blocking OCR hook as a guardrail so its raise propagates (#42775)	2026-09-23 12:18:24 -07:00
support	feat(lint): add LIT013 flagging *-ok suppressions that suppress nothing and remove the 240 stale ones (#42793)	2026-09-23 17:50:09 -07:00
conftest.py	test(rust): isolate callback registries per hypothesis example	2026-09-18 15:57:50 -07:00
test_cache.py	feat(cache): add a guarded native response-cache resolver foundation (#42769)	2026-09-23 13:54:10 -07:00
test_fork_guard.py	refactor(rust): align the cache crates with Python and wire every native backend (#42530)	2026-09-22 13:13:02 -07:00
test_ocr.py	refactor(rust): run OCR through a route-neutral callback contract and a legacy Logging adapter	2026-09-17 21:13:16 -07:00
test_tokenizer.py	feat(tokenizer): preserve Python defaults with opt-in Rust dispatch (#42174)	2026-09-22 04:41:11 +00:00
test_valkey_semantic_cache_native.py	refactor(rust): align the cache crates with Python and wire every native backend (#42530)	2026-09-22 13:13:02 -07:00