llama-stack-mirror/llama_stack/providers/inline/agents/meta_reference/responses
Ashwin Bharambe cfb86f1178 feat(responses): implement usage tracking in streaming responses
Implementation changes:
- Add usage accumulation to StreamingResponseOrchestrator
- Enable stream_options to receive usage in streaming chunks
- Track usage across multi-turn responses with tool execution
- Convert between chat completion and response usage formats
- Extract usage accumulation into helper method for clarity

Test changes:
- Add usage assertions to streaming and non-streaming tests
- Update test recordings with actual usage data from OpenAI
2025-10-10 10:13:33 -07:00
..
__init__.py chore(responses): Refactor Responses Impl to be civilized (#3138) 2025-08-15 00:05:35 +00:00
openai_responses.py feat: reuse previous mcp tool listings where possible (#3710) 2025-10-10 09:28:25 -07:00
streaming.py feat(responses): implement usage tracking in streaming responses 2025-10-10 10:13:33 -07:00
tool_executor.py fix: add traces for tool calls and mcp tool listing (#3722) 2025-10-09 09:59:09 -07:00
types.py feat: reuse previous mcp tool listings where possible (#3710) 2025-10-10 09:28:25 -07:00
utils.py feat(responses)!: add in_progress, failed, content part events (#3765) 2025-10-10 07:27:34 -07:00