mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-13 03:59:12 +00:00
* fix(responses): keep tool_result next to tool_use on Anthropic previous_response_id continuations Replayed history no longer re-adds each stored turn's instructions, and the current request's instructions go before the replayed history instead of between the last tool_use and its tool_result * test(responses): fake the Anthropic transport instead of acompletion in the continuation regression test * fix(responses): keep the previous turn's instructions when a continuation sends none * fix(responses): carry only the latest stored instructions when a continuation sends none Replaying each spend log's own instructions put a system message between a replayed tool_use and its tool_result, which Anthropic rejects with a 400 |
||
|---|---|---|
| .. | ||
| litellm_completion_transformation | ||
| mcp | ||
| __init__.py | ||
| test_additional_tools.py | ||
| test_custom_tool_call.py | ||
| test_dispatch.py | ||
| test_metadata_codex_callback.py | ||
| test_no_duplicate_spend_logs.py | ||
| test_null_test_fix.py | ||
| test_responses_api_bridge_flag.py | ||
| test_responses_api_lifecycle.py | ||
| test_responses_api_request_body.py | ||
| test_responses_prompt_management.py | ||
| test_responses_router_cooldown.py | ||
| test_responses_streaming_iterator.py | ||
| test_responses_supported_endpoints_passthrough.py | ||
| test_responses_utils.py | ||
| test_responses_websocket_all_providers.py | ||
| test_rust_bridge_websocket.py | ||
| test_sse_output_recovery.py | ||
| test_streaming_iterator.py | ||
| test_streaming_iterator_error_events.py | ||
| test_text_format_conversion.py | ||