Run pre_call_hook on Google generateContent endpoints

[Michael-RZ-Berri]

Relevant issues

Adds a hook onto the google generateContent endpoints like everywhere else in the code base.

Linear ticket

Resolves LIT-2706

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/test_litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem
• I have requested a Greptile review by commenting @greptileai and received a Confidence Score of at least 4/5 before requesting a maintainer review

Screenshots / Proof of Fix

Added test that go through guardrails fails before and passes after.

Type

🧹 Refactoring
✅ Test

Changes

Changes google_endpoints/endpoints.py

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

Michael Riad Zaky seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[greptile-apps]

Greptile Summary

This PR refactors the google_generate_content and google_stream_generate_content endpoints to delegate through ProxyBaseLLMRequestProcessing.base_process_llm_request, bringing them in line with the rest of the proxy and enabling the full pre_call_hook / guardrail pipeline. The generationConfig → config field mapping is moved from the endpoint handlers into route_request in route_llm_request.py, and new tests in test_route_llm_request.py verify the transformation at that layer.

Confidence Score: 5/5

Safe to merge — the refactor is consistent with existing proxy patterns and no regressions were identified.

Only a P2 test-gap finding; no P1 or P0 issues found. Core change correctly routes through the hook pipeline.

tests/test_litellm/proxy/test_route_llm_request.py — minor assertion gap in test_route_request_preserves_existing_config_for_google_routes

Important Files Changed

Filename	Overview
litellm/proxy/google_endpoints/endpoints.py	Both google_generate_content and google_stream_generate_content now delegate to ProxyBaseLLMRequestProcessing.base_process_llm_request, enabling the full pre/during/post-call hook pipeline (including guardrails); generationConfig → config mapping moved to route_request.
tests/test_litellm/proxy/google_endpoints/test_google_api_endpoints.py	Tests refactored to mock at the ProxyBaseLLMRequestProcessing level; previous end-to-end assertions replaced with processor-invocation checks; coverage of generationConfig → config transformation moved to test_route_llm_request.py.
tests/test_litellm/proxy/test_route_llm_request.py	New parametrized tests verify generationConfig → config mapping and preservation logic in route_request; minor gap: the "preserve existing config" test doesn't assert generationConfig is removed from forwarded kwargs.

_{Reviews (2): Last reviewed commit: "run pre_call_hook on Google generateCont..." | Re-trigger Greptile}

[Michael-RZ-Berri]

@greptile-ai