mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-12 12:06:04 +00:00
Implements missing streaming events from OpenAI Responses API spec: reasoning text/summary events for o1/o3 models, refusal events for safety moderation, annotation events for citations, and file search streaming events. Added optional reasoning_content field to chat completion chunks to support non-standard provider extensions. Refactored streaming orchestrator to handle new content types via helper methods. |
||
|---|---|---|
| .. | ||
| img | ||
| providers/vector_io | ||
| deprecated-llama-stack-spec.html | ||
| deprecated-llama-stack-spec.yaml | ||
| experimental-llama-stack-spec.html | ||
| experimental-llama-stack-spec.yaml | ||
| llama-stack-spec.html | ||
| llama-stack-spec.yaml | ||
| remote_or_local.gif | ||
| safety_system.webp | ||
| site.webmanifest | ||
| stainless-llama-stack-spec.html | ||
| stainless-llama-stack-spec.yaml | ||