litellm/tests/unit/proxy/_experimental
VimarshDwivedi 22c9e383f3
fix(mcp): let tool-argument validation calls set their own timeout budget (#46184)
test_cold_concurrent_schema_validation_accepts_valid_arguments pins the
process to a single CPU core and fans out 8 concurrent calls through
anyio.to_process's subprocess worker pool, each needing to cold-spawn a
fresh interpreter and import jsonschema. Under a slow or contended CI
runner that routinely exceeds the production 30-second budget before any
actual validation work runs, failing the test on a genuine timeout rather
than a validation bug.

_tool_argument_validation_error now takes an optional timeout_seconds,
defaulting to the existing constant, so production behavior is
unchanged. The test passes a timeout sized for its own single-core,
cold-start stress scenario, matching the margin the companion
integration test (test_schema_validation_stops_expensive_work_and_recovers)
already grants a similar concurrency=8 case.
2026-10-13 17:15:22 +00:00
..
mcp_server fix(mcp): let tool-argument validation calls set their own timeout budget (#46184) 2026-10-13 17:15:22 +00:00
__init__.py ci: move provider-independent MCP tests into tests/unit and run mcp-integration from litellm-tests (#42904) 2026-09-24 23:07:48 +00:00