Commit graph

9 commits

Author SHA1 Message Date
yujonglee
8302f006dd
refactor(rust-bridge): return an unstarted Execution from native entrypoints and drive it in Python (#46299)
* refactor(rust-bridge): return an unstarted Execution from native entrypoints and drive it in Python

Rust's run_call built Python streams itself and imported
litellm.rust_bridge.streams by name, so sync calls were driven in Rust
while async calls came back as a Rust-made coroutine. Every native
inference entrypoint now returns one unstarted Execution and
public_execution.py drives it with lifecycle.run or lifecycle.drive,
wrapping streams and _hidden_params on the Python side. Rust only
imports the lifecycle step classes through StepTypes, and
python-bridge/src/lifecycle.rs, PythonLifecycle and streams.py are gone.

The adapter trusts the _native.pyi contract with a single cast instead
of a per-request runtime_checkable isinstance. Binding tests assert the
adapter starts the execution and returns its completed value rather
than checking callable identity.

* refactor(rust-bridge): fold lifecycle and public_execution into one execution module

The public stream wrappers only forwarded to the lifecycle streams and added the
header dict, so the streams now carry _hidden_params themselves. lifecycle.py no
longer held any call lifecycle, just the Execution driver, so it is renamed to
execution.py and absorbs the synchronous and asynchronous adapters

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

* fix(rust-bridge): keep execution.py free of third-party imports

The host-python tests load execution.py into a bare interpreter, so the
pydantic header validation broke them. The stream head comes from the
binding's encode_stream_head, which always builds a str-keyed dict

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

* test(host-python): preserve pre-async hook coverage after execution handoff

* style(rust-bridge): sort litellm_host_python imports

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* test(rust-bridge): drive unstarted native calls through execution in the split lifecycle tests

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* fix(rust-bridge): mark execution TypeVar as Final

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* test(rust-bridge): cover stream close, read failure, and sync suspension in execution

Co-Authored-By: Yujong Lee <yujong@berri.ai>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-14 17:50:44 -07:00
yujonglee
f50f14117f
refactor(rust-bridge): generator-style execution protocol with stream step names (#46282)
* refactor(rust-bridge): drive executions with generator-style send, throw and close

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* refactor(rust-bridge): name stream steps StreamOpen and StreamChunk and reject out-of-phase steps

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* refactor(rust-bridge): drive with ExitStack and require the stream factory

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* test(host-python): give the hook_chain lifecycle binding the stream factory

Co-Authored-By: Yujong Lee <yujong@berri.ai>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-14 17:19:07 -07:00
yujonglee
7d4be1e217
refactor(host-python): run the Python driver as one async body (#46235)
* refactor(host-python): run the Python driver as one async body

Co-Authored-By: Yujong Lee <yujong@berri.ai>

* refactor(host-python): give the driver a PythonCaller with named suspensions

PythonTask becomes PythonCaller with await_python, open_stream and yield_chunk, so the call body no longer builds Suspension values or maps stream replies itself

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

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:19:06 -07:00
yujonglee
ab0875b2da
refactor(host-python): collect host failures in a thiserror Error enum (#46361)
* refactor(host-python): collect host failures in a thiserror Error enum

missing_state() and the inline PyRuntimeError/PyTypeError messages become Error variants with one From<Error> for PyErr, and InvokeError derives thiserror so From<PyErr> comes from #[from]

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

* docs(host-python): note the canonical HostError import alias in AGENTS.md

Co-Authored-By: Yujong Lee <yujong@berri.ai>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-14 17:19:06 -07:00
yujonglee
327bdcaa7f
test(host-python): move driver tests out of the inline module (#46325)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-14 17:19:05 -07:00
yujonglee
ec605826d4
feat: improve trace ingestion and trace details (#43975)
* refactor: separate OTLP HTTP decoding from trace codec

* feat: complete trace ingestion and read paths

* fix: encode OTLP protobuf errors in Rust

* fix: raise OTLP body limit to 16 MiB

* test: cover OTLP auth body parsing boundary

* refactor: parse OTLP media type into enum

* fix: enforce OTLP body size at HTTP boundary

* perf: preserve shared OTLP metadata across ingestion

* bench: compare owned and shared trace resource fanout

* refactor: extract shared storage and Python conversion caches

* refactor: keep shared storage owned by traces

* test: keep trace loopback coverage in Rust

* test(proxy): adapt trace coverage to injected access context

* fix(tracing): satisfy stacked branch lint checks

* refactor(tracing): use immutable ingestion payloads

* fix(tracing): declare native error encoder export

* test(proxy): resolve trace access through dependency

* fix(tracing): align merged normalizer types and bridge tests

* fix(tracing): address ingestion and diagnostic review findings

* fix(proxy): preserve body parsing for partial request scopes

* test(proxy): use valid HTTP scopes in request fixtures

* test(proxy): complete auth request flow scopes
2026-10-01 13:45:33 -07:00
devin-ai-integration[bot]
5e38a08741
feat(cache): select Rust caching through explicit cache objects (#43601)
* refactor(cache): organize v2 cache as a package

* docs: clarify experimental v2 guidance

* fix(cache): verify cache-hit accounting and preserve logging metadata

* refactor(cache): separate execution facts from host accounting

* refactor(rust): build messages routes with named dependencies

* wip

* fix(cache): preserve facade policy and preflight fallback

* refactor(cache): defer shared Python logging changes

* test(gateway-inference): allow dead code in shared test helpers

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

* fix(cache): key prepared requests and honor facade controls

* feat(cache): use Python caches from Rust Messages inference

* refactor(cache): separate native and Python cache adapters

* refactor(cache): enforce shared composition and adapter boundaries

* fix(cache): let Python key delegated Rust Messages entries

---------

Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-29 00:01:44 +00:00
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
Yujong Lee
63d994ade4 refactor(rust): run OCR through a route-neutral callback contract and a legacy Logging adapter
Extracted from #41733 without the router loop, the cache machine layer, streaming, or the
error, timeout and route-pruning work that moved to #41745

litellm-callbacks holds the contract a native call and its host share: Machine, HostOp,
CallEvent, the in-process run loop, and Passthrough, which is built only by comparing the
caller's inputs with the body the route sends, so a route can never mark a key it rewrote.
litellm-host-python (formerly python-interop) owns the CPython driver and the Execution
handle, and litellm-callbacks-legacy is the @client wrapper as the native call sees it:
function_setup, the deployment hooks, pre_call and post_call, the success and failure fan-out
and the deferred proxy release. OCR is the one route on it, and the old core and bridge
lifecycles are gone

The passthrough rule is the structural fix for the bug #41719 patched in core and #41716
reworks: an inlined remote document no longer counts as the caller's value, so the legacy
adapter never hands the caller's URL back into the body. core/tests/ocr/passthrough.rs pins
it for every route and document source, including that unchanged values stay passthrough,
and callbacks-legacy/tests/payload.rs pins the adapter side with a real pre_call callback

Python OCR integration tests that only exercised core behavior now live as Rust tests, so
tests/test_litellm_rust keeps the cases that need the full Python stack
2026-09-17 21:13:16 -07:00