Commit graph

22 commits

Author SHA1 Message Date
Yujong Lee
80dbb2a28a refactor(rust): resolve the http client config through From and TryFrom
HttpClientConfig::resolve becomes From<&HttpSettings> for Resolution and client_builder becomes TryFrom<&HttpClientConfig> for reqwest::ClientBuilder, matching the rustls conversion. The verify decision moves into From<&HttpSettings> for Verify, and the proxy environment rule moves next to its flags as HttpSettings::trusts_proxy_env. The curve and cipher results are read with transpose and a default selection, which removes the tuple destructuring
2026-09-18 19:48:34 -07:00
Yujong Lee
51010ea486 feat(rust): serve every gateway HTTP setting natively instead of declining to Python
litellm-http now builds the rustls config itself, so one route-neutral place covers roots, the client certificate, ALPN, ssl_ecdh_curve and ssl_security_level. A curve picks the single key exchange group. A cipher string restricts the TLS 1.2 suites it names, and entries rustls cannot express, such as @SECLEVEL=1, are logged once and skipped.

user_url_validation and user_url_allowed_hosts are applied by the media fetcher. Document downloads honor the environment proxy whenever provider calls do, keeping the per-hop address check, and stay on the pinned resolver when no proxy applies.

AIOHTTP_SO_KEEPALIVE, AIOHTTP_TCP_KEEPIDLE, AIOHTTP_TCP_KEEPINTVL, AIOHTTP_TCP_KEEPCNT and AIOHTTP_KEEPALIVE_TIMEOUT map onto the client. A client= argument and a live SSLContext are ignored
2026-09-18 19:39:07 -07:00
Yujong Lee
b2d6cd1fcf refactor(rust): read litellm HTTP globals through one Python shim and tighten the http pool
Drop the core ocr() facade so VertexAuth and the http pool stay out of litellm-core's
public API, move the http Error enum to error.rs, and inject the media DNS resolver into
HttpClientPool instead of a per-call builder hook the cache key ignored.

The bridge now reads litellm.* HTTP settings only through litellm/rust_bridge/settings.py,
pinned by python_settings.json, while env overrides stay in Rust. This adds the Python
default User-Agent, parses string ssl_verify globals like get_ssl_verify, drops per-call
ssl_verify that Python OCR never honored, and removes the unused request_timeout.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-18 17:23:26 -07:00
Yujong Lee
b6b5ef00cc chore: merge main into litellm_rust_http_pool_ocr
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-19 00:10:17 +00:00
Yujong Lee
5a474fd799 refactor(rust): inject VertexAuth into OcrClient so the bridge keeps one token cache
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 23:31:27 +00:00
Yujong Lee
abb9618971 feat(rust): add litellm-http client pool and inject it into the OCR route
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 23:28:11 +00:00
Yujong Lee
19ffb584eb refactor(rust): rename litellm-callbacks to litellm-host and HostOpError to InvokeError 2026-09-18 15:45:08 -07:00
Yujong Lee
3a5b7c12ef refactor(rust): separate machine events from the Python lifecycle's events 2026-09-18 15:45:08 -07:00
Yujong Lee
1a52bae779 add streaming message 2026-09-18 15:45:08 -07:00
Yujong Lee
b4bfd92a2a refactor(rust): route-neutral callback contract
Every legacy callback call from callbacks-legacy now goes through one typed
Python shim, litellm.rust_bridge.legacy_callbacks, the only Python module
the crate reaches. Before, the crate called Logging methods, litellm.utils
hooks, the logging worker, the executor and several litellm globals
directly, and its tests retyped those signatures by hand, so an outdated
fake could accept a call the real code rejects. python_contract.json lists
each shim function's parameters: a Python test pins it to the real
signatures and a Rust test pins it to the Rust enum.

The lifecycle contract changes to match the Python @client wrapper:
- the driver emits CallEvent::Started before begin, so every host sees one
  start time
- RequestContext carries the route-resolved api_key, so legacy pre_call and
  post_call receive it, and post_call's additional_args match the Python OCR
  path
- Passthrough and its re-aliasing are gone
- async deployment hooks always run, and the "no callbacks" shortcut that
  skipped the logging payload is removed, as in the Python path

The OCR api_key is a SecretValue from the wire request onward, so Debug
output upstream of the callback contract cannot leak it.

host-python's RouteHost now classifies native failures once through
classify, and host ops return HostOpError. The OCR route host keeps main's
public errors by sending both through the existing Python map_failure.
2026-09-18 15:43:08 -07:00
Yujong Lee
5a76346047 refactor(rust): move OCR provider code into litellm-llms and delete core/src/llms
OCR transformations, BaseOcrConfig with its response and connection types,
the OCR error, and the HTTP pieces (custom_httpx: http_handler, transport,
media, llm_http_handler with OcrClient and the request/response handler)
now live in litellm-llms at their Python paths. Provider code no longer
reaches into the route: it gets the caller's hooks through a route-neutral
CallHooks trait that core implements over its host, and core dispatches to
llm_http_handler::ocr with the concrete config, the way Python calls
base_llm_http_handler.ocr(provider_config=...).

Core keeps the route: entrypoint, request types, credential fallback,
provider dispatch, the machine and hook glue. ocr/mod.rs no longer
re-exports anything, provider constants moved next to their only users,
and provider tests that drive the whole route moved to core's route test
files. Twenty-two of those were exact copies of tests already there and
were dropped; every one still runs once.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-17 22:29:08 -07:00
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
Yujong Lee
f1ea94fee7 make test pass 2026-09-17 08:55:59 -07:00
Yujong Lee
370cdaabf9 encode failing tests 2026-09-17 08:04:52 -07:00
Yujong Lee
85e70ea374 fix(ocr): await blocking preparation on cancellation 2026-09-16 20:49:31 -07:00
Yujong Lee
e0ce998091 fmt 2026-09-16 20:21:51 -07:00
Yujong Lee
edfa01da81 refactor(ocr): mirror Python provider layout and preserve tests 2026-09-16 19:48:26 -07:00
Yujong Lee
c621435ef7 refactor(ocr): move file preparation from the python bridge into litellm-core
Delete litellm/ocr/input.py and the native _ocr_file_document, _ocr_upload_document
and _ocr_mime_type helpers. File documents now project to a typed OcrDocumentInput
and the core lifecycle reads local paths, encodes bytes and asks the host to read
file-like objects through a ReadDocument operation before the provider request

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 21:02:30 +00:00
Yujong Lee
23633445d7 refactor(rust): extract auth and cache crates
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-16 18:12:11 +00:00
yujonglee
347b642bdd
refactor(ocr): complete native lifecycle and preserve Azure auth (#40734)
* refactor(ocr): extract call completion boundary

* fix(ocr): release completion state after dispatch

* test(ocr): prove wrapper completion handoff

* test(ocr): narrow mapped failure assertion

* fix(ocr): preserve wrapper invocation kwargs

* fix(ocr): retain completion through finalization

* fix(ocr): make completion ownership explicit

* refactor(ocr): resolve logging executor explicitly

* fix(callbacks): preserve completion lifecycle behavior

* refactor(ocr): move public OCR into native lifecycle

* refactor(ocr): remove unused rust bridge capability

* wip

* wip

* refactor

* wip

* fix(ocr): preserve reducto native compatibility

* wip

* fix(ocr): document native callable casts

* perf(ocr): bound responses and reduce native scheduling overhead

* refactor(python-bridge): organize placeholder routes

* refactor test

* fix(ocr): normalize DeepSeek document content

* perf(ocr): skip unused callback work and benchmark callback overhead

* fix(ocr): align conversion contracts

* test(ocr): cover official provider response shapes

* fix(ocr): restore Python fallback and honor Rust opt-out

* fixes and refactor

* fix(ocr): preserve Azure Document Intelligence authentication

* fix(rust): enforce OCR response limits and lint contracts

* test(rust): align native OCR contract coverage

* test(ocr): isolate Azure auth precedence coverage
2026-09-12 11:56:49 -07:00
yujonglee
5e23db8e03
feat(ocr): add Azure Mistral adapter with native authentication (#40502)
* feat(ocr): move Azure credential resolution to Rust

* fix(auth): keep shared primitives warning-free

* fix(auth): preserve missing key provider errors

* fix(auth): enforce Azure input provenance

* fix(ocr): preserve proxy credential provenance
2026-09-11 16:22:55 -07:00
yujonglee
b0d66a15b8
feat(ocr): add core foundation and Mistral adapter (#40530)
* feat(ocr): add core foundation and transport primitives

* fix(ocr): decline missing Mistral credentials

* fix(rust): compile trace parity on Rust 1.98

* refactor(ocr): define native response capability

* refactor(auth): generalize missing API key errors

* refactor(core): keep URL helpers usage scoped

* refactor(ocr): support native responses across adapters

* refactor(ocr): preserve unmapped provider params

* refactor(ocr): distinguish request preparation from payload transforms

* refactor(ocr): trace payload transformation at codec boundary
2026-09-10 13:18:41 -07:00