Mateo Wang daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422) ... * test(mcp): cover one spend row billing both rounds of a chat completions MCP auto-execute * fix(mcp): bill both model calls of a chat completions MCP auto-execute on one spend row * fix(mcp): keep provider usage fields when summing both chat rounds of an MCP auto-execute * fix(mcp): log each auto-executed MCP tool call under its own spend-log id A chat MCP auto-execute logged its tool calls under the request's call id, which is also the id of the request's failure row. When the follow-up call failed, the database kept the tool row and dropped the failure row that bills the paid first call * test(mcp): cover the margin, cache, failure row and parallel tool rows of MCP auto-execute billing		2026-10-20 04:37:31 +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
conftest.py	perf(ci): isolate and shard integration suites (#44146)	2026-10-10 11:15:19 -07:00
test_aresponses_api_with_mcp.py	fix(responses): log and bill every round of non-stream MCP auto-execute (#43667)	2026-10-16 17:37:33 +00:00
test_chat_completions_handler.py	fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)	2026-10-20 04:37:31 +00:00
test_litellm_proxy_mcp_handler.py	fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)	2026-10-20 04:37:31 +00:00
test_mcp_streaming_iterator.py	fix(responses): open faked stream items empty so tool arguments and text arrive once (#46533)	2026-10-15 09:35:12 -07:00
test_round_billing.py	fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)	2026-10-20 04:37:31 +00:00
test_tool_precheck.py	fix(sdk): decide MCP gateway routing without importing the proxy handler (#45961)	2026-10-20 01:44:54 +00:00