litellm/tests/test_litellm/rust_bridge/AGENTS.md
devin-ai-integration[bot] 19556952d9
feat(secrets): route secret resolution through native Rust backends (#42619)
* fix(secrets): verify provider API request and payload contracts

* wip

* fix(secrets): unify backend reads and route secret resolution

* feat(secrets): bind built-in managers to retained Rust backends

* refactor(secrets): centralize catalog dispatch and native binding

* test(secrets): split provider integration tests

* refactor(secrets): enforce cache and rotation contracts

* test(secrets): stub parent packages in failing resolver fixture

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

* refactor(secrets): pass manager settings through the interop boundary

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

* fix(secrets): align cloud KMS auth and harden provider reads

* ci(rust): raise native wheel size gate to 40 MB for secrets backends

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

* fix(proxy): treat unset google kms flag as disabled like the old loader

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

* fix(secrets): preserve certificate credentials and disabled KMS flags

* test(secrets): cover certificate validation and bounded auth retries

* test(secrets): cover Python dispatch without the native extension

* test(proxy): skip legacy secret manager cases when the optional SDK is missing

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

* fix(secrets): port Python parity tests and preserve provider behavior

* fix(secrets): store the captured native config without setattr to satisfy the strict lint budget

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

* fix(secrets): preserve missing Azure manager values

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

* test(secrets): pin typed values and recovery failure precedence

* refactor(secrets): organize provider internals and behavioral test suites

* refactor(secrets): simplify recovery and isolate Python compatibility

* fix(secrets): distinguish Azure callback absence from HTTP not found

* fix(secrets): preserve Python AWS read results at the bridge

* fix(secrets): route public reads through the native catalog bridge

* fix(secrets): keep JSON selection outside the bridge

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

* fix(secrets): preserve provider JSON reads at the bridge

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

* fix(secrets): preserve Python primary JSON semantics

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

* fix(secrets): preserve CyberArk mutation behavior through the native bridge

* docs(secrets): record public API replacement gaps

* refactor(secrets): share Vault write payload preparation

* feat(secrets): route Vault mutations through the native bridge

* fix(secrets): preserve typed Vault rotation failures

* refactor(secrets): move Python dispatch into bridge

* refactor(secrets): move CyberArk Python policy into bridge

* refactor(secrets): move Vault Python policy into bridge

* test(secrets): assert Vault rotation request paths

* fix(secrets): keep bridge JSON interop centralized

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: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-23 08:24:57 -07:00

1.1 KiB

Rust bridge tests

Test what each side of the bridge does, not the rollout policy that picks a side. LITELLM_RUST and catalog.RULES change every time a route or backend rolls forward, so a test that sets the env var or patches the catalog to reach a path goes red on a policy change even when the code under test is fine

Call each path directly with an explicit decision instead. The Python path is the implementation the dispatcher falls back to, e.g. litellm.ocr.main.ocr. The Rust path is the native binding, e.g. NATIVE_OCR.load() from litellm/rust_bridge/ocr/entrypoints.py, called with the request, args and kwargs that dispatch would hand it. When the native side reads a policy-derived setting such as settings.secret_manager().native, pin that field in the test instead of deriving it from the catalog. ocr/test_secrets.py shows the pattern

Rollout policy itself, meaning which rule matches and what LITELLM_RUST changes, belongs in test_catalog.py, test_configuration.py and test_dispatch.py, tested against rules the test builds rather than the shipped catalog.RULES