mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-08 08:08:37 +00:00
Providers like Mistral put every parallel tool call, with full arguments, into one
chat-completions chunk. The /v1/messages adapter opened one tool_use block for the
first call and concatenated every call's arguments into it, so clients got invalid
JSON like {...}{...}. _CombinedChunkSplitter now splits such a chunk into one chunk
per call. The first call streams live and calls opened behind it are held, gathering
their fragments by index, until a non-fragment chunk arrives or the stream ends
Fixes #44029
|
||
|---|---|---|
| .. | ||
| test_anthropic_messages_fireworks_stop_wire.py | ||
| test_anthropic_messages_hosted_vllm_reasoning_wire.py | ||
| test_chat_bridge_mid_stream_failure_bookkeeping_wire.py | ||
| test_chat_bridge_multi_tool_call_blocks_wire.py | ||
| test_chat_bridge_pre_content_retry_wire.py | ||