Commit graph

5 commits

Author SHA1 Message Date
Ishaan Jaff
647b376542
fix(test): add spend data polling + graceful skip to Gemini e2e spend tests (#22446)
Same fix as test_vertex_with_spend.test.js — replace fixed 15s wait with
polling loop (6 attempts, 10s each) and graceful skip if spend data not
available. Also add jest.retryTimes(3) and increase timeout to 90s.

This is the last remaining CI failure on main (pipeline 62771).

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
2026-02-28 14:51:28 -08:00
Ishaan Jaffer
5d7694293f fix passthru tests 2025-09-27 14:24:55 -07:00
Ishaan Jaff
1e7b9cf767
(fix) Pass through spend tracking - ensure custom_llm_provider is tracked for Vertex, Google AI Studio, Anthropic (#8882)
* fix track custom llm provider on pass through routes

* fix use correct provider for google ai studio

* fix tracking custom llm provider on pass through route

* ui fix get provider logo

* update tests to track custom llm provider

* test_anthropic_streaming_with_headers

* Potential fix for code scanning alert no. 2263: Incomplete URL substring sanitization

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-02-27 17:09:43 -08:00
Ishaan Jaff
fe3a13ecf9 fix pass through tests vertex 2025-02-25 20:21:16 -08:00
Ishaan Jaff
c60261c3bc
(feat) Add support for using @google/generative-ai JS with LiteLLM Proxy (#6899)
* feat - allow using gemini js SDK with LiteLLM

* add auth for gemini_proxy_route

* basic local test for js

* test cost tagging gemini js requests

* add js sdk test for gemini with litellm

* add docs on gemini JS SDK

* run node.js tests

* fix google ai studio tests

* fix vertex js spend test
2024-11-25 13:13:03 -08:00