llama-stack/llama_stack/providers
Ashwin Bharambe bfdd15d1fa
fix(responses): use input, not original_input when storing the Response (#2300)
We must store the full (re-hydrated) input not just the original input
in the Response object. Of course, this is not very space efficient and
we should likely find a better storage scheme so that we can only store
unique entries in the database and then re-hydrate them efficiently
later. But that can be done safely later.

Closes https://github.com/meta-llama/llama-stack/issues/2299

## Test Plan

Unit test
2025-05-28 13:17:48 -07:00
..
inline fix(responses): use input, not original_input when storing the Response (#2300) 2025-05-28 13:17:48 -07:00
registry feat: accept MCP authorization headers for MCP toolgroups (#2230) 2025-05-23 08:52:18 -07:00
remote fix: convert boolean string to boolean (#2284) 2025-05-27 13:05:38 -07:00
utils fix: chat completion with more than one choice (#2288) 2025-05-27 15:39:15 -07:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
datatypes.py fix(tools): do not index tools, only index toolgroups (#2261) 2025-05-25 13:27:52 -07:00