mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
4ccc32312d
test_basic_vertex_ai_pass_through_with_spendlog failed intermittently on litellm_internal_staging (pipelines 82155, 82196, 82209, 82230) with "Spend should be greater than before after 120s". Spend logging is async and batched, so the pass-through call's cost sometimes had not landed within the 120s poll window; one run ended on spend_after 0.0 because the final /global/spend/logs read returned nothing and "or 0.0" recorded that as zero spend. Widen the poll window to 240s and skip a transient empty read instead of treating it as 0.0, so a momentary endpoint hiccup on the last poll no longer fails an otherwise-billed call. The spend_after > spend_before assertion is unchanged, so a genuinely unbilled call still fails the test |
||
|---|---|---|
| .. | ||
| ruby_passthrough_tests | ||
| base_anthropic_messages_test.py | ||
| package-lock.json | ||
| package.json | ||
| test_anthropic_passthrough.py | ||
| test_anthropic_passthrough_basic.py | ||
| test_anthropic_passthrough_python_sdkpy | ||
| test_assembly_ai.py | ||
| test_gemini.js | ||
| test_gemini_with_spend.test.js | ||
| test_hosted_vllm_passthrough.py | ||
| test_local_gemini.js | ||
| test_local_vertex.js | ||
| test_mcp_routes.py | ||
| test_openai_assistants_passthrough.py | ||
| test_vertex.test.js | ||
| test_vertex_ai.py | ||
| test_vertex_with_spend.test.js | ||
| vertex_key.json | ||
| vertex_test_helpers.js | ||