mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-06 02:48:13 +00:00
Fixes #18381: When using both tools and response_format with Bedrock Converse API, LiteLLM internally adds json_tool_call to handle structured output. Bedrock may return both this internal tool AND real user-defined tools, breaking consumers like OpenAI Agents SDK. Changes: - Non-streaming: Added _filter_json_mode_tools() to handle 3 scenarios: only json_tool_call (convert to content), mixed (filter it out), or no json_tool_call (pass through) - Streaming: Added json_mode tracking to AWSEventStreamDecoder to suppress json_tool_call chunks and convert to text content - Fixed optional_params.pop() mutation issue Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| chat | ||
| count_tokens | ||
| embed | ||
| files | ||
| image | ||
| invoke_agent | ||
| messages/invoke_transformations | ||
| passthrough | ||
| realtime | ||
| rerank | ||
| vector_stores | ||
| test_anthropic_beta_support.py | ||
| test_base_aws_llm.py | ||
| test_bedrock_common_utils.py | ||
| test_bedrock_ssl_verify.py | ||
| test_cross_region_inference_profile_mapping.py | ||