scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-23 00:41:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81
litellm/tests/pass_through_unit_tests
History
Cursor Agent 3390fc1972
test(vcr): mark Bedrock prompt-caching cross-call tests VCR-incompatible 
The pass_through prompt-caching tests
(test_prompt_caching_returns_cache_read_tokens_on_second_call,
test_prompt_caching_streaming_second_call_returns_cache_read) make a
warm-up call and then assert the *second* call sees a non-zero
cache_read_input_tokens count from the upstream's prompt-cache. VCR
replay can't model cross-call provider state — both calls match the
same cassette episode, so the second call returns the first call's
pre-warmup response and the assertion fails:

    AssertionError: Expected cache_read_input_tokens > 0 on second call,
    but got 0. Full usage: {'input_tokens': 4986,
    'cache_creation_input_tokens': 4974, 'cache_read_input_tokens': 0}

This started biting after the AWS SigV4 fingerprint stabilization
(b637d9f64a): Bedrock requests now produce a stable per-access-key
fingerprint instead of a per-request signature, so cassettes
successfully replay where they previously always missed and re-recorded
live. Opt these tests out via skip_nodeid_suffixes so they run live and
match the existing pattern in tests/llm_translation/conftest.py
(::test_prompt_caching).

Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-13 01:19:03 +00:00
..
messages_api_structured_output style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
base_anthropic_messages_prompt_caching_test.py fix(tests): use Sonnet 4.5 for Bedrock invoke prompt-caching tests 2026-04-28 14:51:47 -07:00
base_anthropic_messages_tool_search_test.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
base_anthropic_unified_messages_test.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
conftest.py test(vcr): mark Bedrock prompt-caching cross-call tests VCR-incompatible 2026-05-13 01:19:03 +00:00
test_anthropic_messages_passthrough.py replace retired claude-3-haiku-20240307 with claude-haiku-4-5-20251001 in anthropic messages passthrough test 2026-04-20 15:44:11 -07:00
test_anthropic_messages_prompt_caching.py fix(tests): use Sonnet 4.5 for Bedrock invoke prompt-caching tests 2026-04-28 14:51:47 -07:00
test_anthropic_messages_tool_search.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_assemblyai_unit_tests_passthrough.py fix: block path traversal SSRF in BitBucket, Arize Phoenix, and AssemblyAI clients (#26943) 2026-05-01 11:45:12 -07:00
test_bedrock_anthropic_messages_test.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_bedrock_tool_use_beta_header.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_claude_code_marketplace.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_custom_logger_passthrough.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_pass_through_unit_tests.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_passthrough_registry_updates.py Fix passthrough tests 2026-02-20 17:28:06 -08:00
test_unit_test_anthropic_pass_through.py Fix CI: Revert security scan changes and add GitGuardian ignore rules (#18358) 2025-12-22 17:03:53 -08:00
test_unit_test_passthrough_router.py test_get_credentials_from_env 2026-03-30 16:02:14 -07:00
test_unit_test_streaming.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_vertex_ai_anthropic_streaming_cost_injection.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_vertex_ai_live_passthrough.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_websearch_interception_e2e.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00