scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-12 23:01:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 88
litellm/tests
History
Exact
Yassin Kortam 2f5e4c5ae4 fix(bedrock): explain why Anthropic's web_search server tool is rejected 
Bedrock hosts none of Anthropic's web_search server tools, so forwarding
one earns an opaque "The provided request is not valid" from AWS that
names neither the tool nor a way forward. Every Claude model on Bedrock
fails the same way, which reads as a broken deployment rather than an
unsupported capability.

Reject it in the Bedrock Invoke messages transform with a message naming
the tool and the web-search interception settings that do serve it.
Interception rewrites the tool into LiteLLM's own search tool before this
point, so the guard only fires when it is not configured and the working
path is untouched.

Resolves LIT-5391
2026-08-10 16:07:11 -07:00
..
agent_tests test: repair stale CircleCI contracts 2026-08-08 12:19:29 -07:00
audio_tests
base_sdk_tests fix(deps): move pydantic-settings into the base dependencies 2026-08-01 15:25:26 -07:00
basic_proxy_startup_tests
batches_tests test(batches): run Responses coverage in CI 2026-07-31 10:24:10 -04:00
benchmarks test(benchmarks): run shared logging executor inline to make CodSpeed measurements deterministic (#32435) 2026-07-09 11:14:22 +03:00
code_coverage_tests fix(guardrails): scan /v1/messages tool traffic 2026-08-05 14:11:27 -07:00
documentation_tests fix(ci): make the env-key doc gate see bare get_secret and get_secret_str reads (#35996) 2026-08-05 14:49:55 -07:00
e2e Merge pull request #36277 from BerriAI/litellm_make_check_fallback 2026-08-08 12:08:34 -07:00
enterprise fix(proxy): report has_more false on caller-scoped file list pages 2026-08-08 17:28:43 -07:00
guardrails_tests fix(guardrails): honor configured timeout in Zscaler AI Guard (#36110) 2026-08-07 00:25:52 +00:00
image_gen_tests test(bedrock): switch image gen live test off EOL Titan to Nova Canvas (#31937) 2026-07-01 22:57:29 -07:00
integration
litellm fix(proxy): deny agent access when key and team grants resolve to nothing (#36221) 2026-08-07 20:44:11 +00:00
litellm-proxy-extras
litellm_core_utils
litellm_utils_tests test: repair stale CircleCI contracts 2026-08-08 12:19:29 -07:00
llm_responses_api_testing test: repair stale CircleCI contracts 2026-08-08 12:19:29 -07:00
llm_translation test(bedrock): port the openai-route invoke tests onto the live config 2026-07-29 20:59:08 -07:00
load_tests
local_testing test: repair three failing suites on litellm_internal_staging 2026-08-04 16:07:02 -07:00
logging_callback_tests feat(logging): add opt-in session_id and trace_id correlation to JSON log records via contextvars (#34418) 2026-08-10 10:40:13 -07:00
mcp_tests fix(mcp): keep REST tool listing in step with key/team grant enforcement 2026-07-30 22:13:10 -07:00
multi_instance_e2e_tests
ocr_tests test(ocr): use mistral-document-ai-2512 in azure_ai OCR tests 2026-07-15 18:13:22 -07:00
old_proxy_tests/tests
openai_endpoints_tests fix(batches): register managed output files on batch cancel 2026-08-05 18:28:52 -07:00
otel_tests fix(cli): mint per-session agent credential on lite login (#31072) 2026-06-26 09:05:15 -07:00
pass_through_tests test(pass-through): de-flake vertex spend-log test by routing through the proxy (#31689) 2026-06-30 15:27:48 -07:00
pass_through_unit_tests fix(proxy): re-assert the authenticated identity on passthrough requests (#36121) 2026-08-07 00:41:29 +00:00
proxy_admin_ui_tests Revert "chore: remove _experimental/out (#31546)" 2026-07-01 13:25:47 -07:00
proxy_behavior test: repair stale CircleCI contracts 2026-08-08 12:19:29 -07:00
proxy_e2e_anthropic_messages_tests
proxy_migration_tests test(docker): gate the componentized gateway and backend images on an arbitrary-uid offline boot (#36136) 2026-08-07 09:57:37 -07:00
proxy_security_tests
proxy_unit_tests feat(router): add per-deployment allowed_fails_policy and cooldown_time override support (#34416) 2026-08-10 11:02:06 -07:00
router_unit_tests feat(router): add per-deployment allowed_fails_policy and cooldown_time override support (#34416) 2026-08-10 11:02:06 -07:00
scim_tests
search_tests feat(tinyfish): make search provider permissive, attribute errors (#31997) 2026-07-03 10:17:11 -07:00
spend_tracking_tests
store_model_in_db_tests feat(team): custom metadata validation hook for team create and update (#33353) 2026-08-03 18:37:45 -07:00
test_litellm fix(bedrock): explain why Anthropic's web_search server tool is rejected 2026-08-10 16:07:11 -07:00
unified_google_tests
vector_store_tests
windows_tests
__init__.py
_fake_openai_endpoint_server.py
_flush_vcr_cache.py
_live_test_helpers.py
_openai_record_replay_proxy.py
_vcr_conftest_common.py
_vcr_redis_persister.py
_ws_vcr.py test(realtime): record and replay websocket traffic in redis vcr cassettes (#32390) 2026-07-08 00:19:06 -07:00
eval_swe_bench.py
fake_openai_endpoint.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
pyrightconfig.json
README.MD
test_anthropic_compaction_usage.py
test_budget_management.py
test_callbacks_on_proxy.py
test_config.py
test_debug_warning.py
test_default_encoding_non_root.py
test_end_users.py
test_entrypoint.py
test_fallbacks.py
test_gpt5_azure_temperature_support.py
test_health.py
test_keys.py
test_litellm_proxy_responses_config.py
test_logging.conf
test_models.py
test_new_vector_store_endpoints.py
test_openai_endpoints.py
test_organizations.py
test_otel_thread_leak.py
test_passthrough_endpoints.py
test_presidio_latency.py
test_proxy_server_non_root.py
test_ratelimit.py
test_resource_cleanup.py
test_service_logger_otel.py fix(langfuse): send v4 ingestion header for otel callback (#33907) 2026-07-18 20:36:51 -07:00
test_spend_logs.py
test_team.py
test_team_logging.py
test_team_members.py
test_users.py

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.