mateo-berri 0ecbfa376b fix(mcp): hold round one's log for the guardrail, bill the chunk cost once, and keep round one's id ... When the follow-up call of a streamed chat MCP auto-execute fails, round one's success log now goes through the proxy's deferred guardrail release instead of straight to the handlers, so a post-call guardrail runs on it and the row carries it. Without a proxy release it logs directly as before The last usage chunk now takes its cost from the combined row's billed total, so a fixed cost margin is counted once in the chunk, as it is on the row. The follow-up's usage chunk is held until the follow-up ends to make that possible The combined row now keeps round one's id, the stream's first chunk id, which matches how a single-round stream is logged		2026-10-28 17:12:00 -07:00
..
litellm_completion_transformation	fix(responses): skip failed spend-log turns when rebuilding a session from previous_response_id (#48647)	2026-10-28 06:47:42 +00:00
mcp	fix(mcp): hold round one's log for the guardrail, bill the chunk cost once, and keep round one's id	2026-10-28 17:12:00 -07:00
__init__.py
test_additional_tools.py
test_custom_tool_call.py
test_metadata_codex_callback.py
test_no_duplicate_spend_logs.py
test_null_test_fix.py
test_responses_api_bridge_flag.py	fix(responses): reject or drop Responses params the chat completions bridge cannot translate (#48655)	2026-10-28 07:11:55 +00:00
test_responses_api_lifecycle.py	fix(router): pass lifecycle events through on background OpenAI responses streams that cannot fall back (#48817)	2026-10-28 12:15:02 -07:00
test_responses_api_request_body.py	fix(responses): forward top-level moderation param to OpenAI (#48708)	2026-10-28 10:33:11 -07:00
test_responses_prompt_management.py	fix(sdk): decide MCP gateway routing without importing the proxy handler (#45961)	2026-10-20 01:44:54 +00:00
test_responses_router_cooldown.py	refactor: expose core private helpers under public names (#44871)	2026-10-07 00:05:27 +00:00
test_responses_streaming_iterator.py	fix(responses)!: bill partial usage on mid-stream failures and report bridged /v1/messages failures to the proxy (#47537)	2026-10-28 13:32:09 -07:00
test_responses_supported_endpoints_passthrough.py
test_responses_utils.py	feat(chatgpt): forward client subscriptions through the gateway (#41522)	2026-10-26 15:44:05 -07:00
test_responses_websocket_all_providers.py	fix(router)!: count native Responses WebSocket turns toward deployment limits and budgets (#45727)	2026-10-19 15:35:20 +00:00
test_rust_bridge_websocket.py	refactor(rust-bridge): require the native extension (#48852)	2026-10-28 13:16:56 -07:00
test_sse_output_recovery.py
test_streaming_iterator.py	fix(responses)!: bill partial usage on mid-stream failures and report bridged /v1/messages failures to the proxy (#47537)	2026-10-28 13:32:09 -07:00
test_streaming_iterator_error_events.py	fix(responses): bill every round of a streamed MCP auto-execute on one spend row (#47445)	2026-10-21 02:56:38 +00:00
test_text_format_conversion.py	refactor: expose core private helpers under public names (#44871)	2026-10-07 00:05:27 +00:00