Files
litellm/tests
75d0d2bd7a fix(openrouter): preserve token counts from streaming usage chunks (#21011)
* docs: add reference to example_openai_endpoint repo for self-hosting fake OpenAI proxy (#21006)

- Updated benchmarks.md with a section on setting up fake OpenAI endpoints
- Updated load_test.md to mention the self-hosted option
- Updated load_test_advanced.md with a tip box about the example repo

Reference: https://github.com/BerriAI/example_openai_endpoint

Co-authored-by: Cursor Agent <cursoragent@cursor.com>

* MCP fixes

* fix(oldteams.tsx): show policies when creating

* fix(proxy/_types.py): ensure mcp rest endpoints can be called by virtual key

ensures UI works with virtual key testing mcp endpoints

* refactor: migrate get object permissions table logic to happen in user api key auth - allows functions to trust user api key object they receive has what they need

* fix(rest_endpoints.py): filter for allowed tools based on what key has access to

* fix(mcp_server_manager.py): ensure only allowed MCP's are returned to the user, via rest endpoints

* Guardrails - add toxic/abusive content filter guardrails

* fix(streaming): preserve usage data from post-finish_reason chunks in OpenAI-compatible streaming

Fixes #16112

OpenRouter and other OpenAI-compatible providers send a usage chunk after
the finish_reason='stop' chunk when stream_options.include_usage is True.
The OpenAIChatCompletionStreamingHandler.chunk_parser() was not passing
the usage field to ModelResponseStream, causing real token counts from the
provider to be lost and falling back to inaccurate estimates.

* fix: resolve merge conflict in test file

- Fix typo in test method name (extra space)
- Move test_prompt_cache_key_in_optional_params to its own class

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-02-13 18:27:22 +05:30
..
2026-01-20 18:37:56 +05:30
2026-02-12 17:53:47 -08:00
2026-02-12 17:53:40 -08:00
2026-01-31 19:08:07 -08:00
2026-01-22 10:50:23 -08:00
2026-01-22 15:21:44 -08:00
2026-02-05 09:40:21 +05:30

In total litellm runs 1000+ tests

[02/20/2025] Update:

To make it easier to contribute and map what behavior is tested,

we've started mapping the litellm directory in tests/test_litellm

This folder can only run mock tests.