tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-15 10:20:58 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
b981fddfaadd95d97dca9df4be3561d5a6f9a2cf
litellm/tests
T
History
Lucas Rothman b981fddfaa fix(gemini): properly catch context window exceeded errors 
Fixes #18282

This PR fixes two issues with Gemini context window error handling:

1. **Pattern matching for Gemini 2.0 Flash**: The previous pattern
   'input token count exceeds the maximum number of tokens allowed'
   doesn't match Gemini 2.0 Flash errors which include dynamic token
   counts like '(2800010)' in the message. Split into shorter patterns
   that work with both formats.

2. **Add context window check to Gemini block**: The
   is_error_str_context_window_exceeded() check was only called for
   OpenAI-compatible providers, not for Gemini/Vertex AI. Added the
   check to the Gemini-specific error handling block.

Test cases added for both Gemini 2.0 Flash and 2.5/3 error formats.
2025-12-19 23:20:04 -08:00
..
agent_tests
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
audio_tests
test_runwayml_tts_async
2025-12-13 16:10:48 -08:00
basic_proxy_startup_tests
Fix: remove merge markdown (#17586)
2025-12-06 05:38:16 -08:00
batches_tests
Add output file id in managed objects for batches
2025-12-16 15:52:07 +05:30
code_coverage_tests
code qa check
2025-12-19 19:00:44 +05:30
documentation_tests
Litellm docs readme fixes (#16107)
2025-10-30 17:05:32 -07:00
enterprise
added extraction of top level metadata for custom lables in prometheus callbacks (#18087)
2025-12-17 11:17:12 +05:30
guardrails_tests
[Feat] Guardrails Load Balancing - Allow Platform admins to load balance between guardrails (#18181)
2025-12-19 00:08:03 +05:30
image_gen_tests
fix lint error
2025-12-19 23:45:37 +05:30
litellm
Merge branch 'main' into litellm_staging_12_16_2025
2025-12-16 21:38:14 +05:30
litellm_utils_tests
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
litellm-proxy-extras
Fix: Distinguish permission errors from idempotent errors in Prisma migrations (#17064)
2025-11-24 20:41:44 -08:00
llm_responses_api_testing
Revert "[Fix] CI/CD - local_testing & mapped tests (#18222)" (#18223)
2025-12-18 14:46:09 -08:00
llm_translation
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
load_tests
…
local_testing
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
logging_callback_tests
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
mcp_tests
feat: add support for using MCPs on /chat/completions
2025-12-10 10:55:33 +09:00
multi_instance_e2e_tests
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00
ocr_tests
vertex ai deepseek doesn't support pdf urls, so skip them
2025-12-19 23:53:17 +05:30
old_proxy_tests/tests
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
openai_endpoints_tests
test_e2e_batches_files
2025-11-27 09:14:43 -08:00
otel_tests
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
pass_through_tests
fix: use vllm passthrough config for hosted vllm provider instead of raising error (#16537)
2025-11-12 09:12:14 -08:00
pass_through_unit_tests
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
proxy_admin_ui_tests
Merge remote-tracking branch 'origin' into litellm_new_user_collision_handling
2025-12-06 19:58:35 -08:00
proxy_security_tests
test fix
2025-10-04 10:57:02 -07:00
proxy_unit_tests
Merge pull request #18236 from BerriAI/litellm_add_background_responses_cost_tracking
2025-12-20 00:14:09 +05:30
router_unit_tests
fix(router): add minimum request threshold for error rate cooldown (#17464)
2025-12-12 04:36:10 -08:00
scim_tests
…
search_tests
[Feat] New Search API Provider - LinkUp Search (#18174)
2025-12-18 14:27:36 +05:30
spend_tracking_tests
fix ocr test
2025-10-31 20:32:03 -07:00
store_model_in_db_tests
test_edit_mcp_server_redacts_credentials
2025-11-26 11:54:11 -08:00
test_litellm
fix(gemini): properly catch context window exceeded errors
2025-12-19 23:20:04 -08:00
unified_google_tests
fix: gooogle GenAI route tests
2025-10-04 10:18:25 -07:00
vector_store_tests
[Feat] Add new Rag Search API / Query API with rerankers (#18217)
2025-12-19 19:05:07 +05:30
windows_tests
…
__init__.py
…
gettysburg.wav
…
large_text.py
…
openai_batch_completions.jsonl
…
README.MD
[Feat] MCP Gateway Fine-grained Tools Addition (#15153)
2025-10-03 10:16:29 -07:00
test_budget_management.py
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00
test_callbacks_on_proxy.py
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
test_config.py
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00
test_debug_warning.py
…
test_end_users.py
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00
test_entrypoint.py
…
test_fallbacks.py
…
test_gpt5_azure_temperature_support.py
Fix: Azure GPT-5 incorrectly routed to O-series config (temperature parameter unsupported) (#16246)
2025-11-07 10:24:27 -08:00
test_health.py
…
test_keys.py
…
test_litellm_proxy_responses_config.py
Add native Responses API support for litellm_proxy provider (#15347)
2025-10-08 18:31:26 -07:00
test_logging.conf
…
test_models.py
test_add_model_run_health
2025-09-27 10:59:25 -07:00
test_openai_endpoints.py
test fix claude-sonnet-4-5-20250929
2025-10-28 19:05:13 -07:00
test_organizations.py
…
test_passthrough_endpoints.py
…
test_ratelimit.py
test_async_rate_limit
2025-11-15 10:34:24 -08:00
test_resource_cleanup.py
…
test_spend_logs.py
[Fix] Security - Remove example API keys with high entropy (#18255)
2025-12-19 10:09:50 -08:00
test_team_logging.py
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00
test_team_members.py
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00
test_team.py
[Fix] CI/CD - Add missing documentation for ENVs & Clean Functionality (#18211)
2025-12-18 13:16:15 -08:00
test_users.py
fix: use fastuuid helper (#14903)
2025-09-25 15:47:01 -07:00

README.MD

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.

Reference in New Issue View Git Blame Copy Permalink