llama-stack/llama_stack/providers/remote
Ashwin Bharambe ce33d02443
fix(tools): do not index tools, only index toolgroups (#2261)
When registering a MCP endpoint, we cannot list tools (like we used to)
since the MCP endpoint may be behind an auth wall. Registration can
happen much sooner (via run.yaml).

Instead, we do listing only when the _user_ actually calls listing.
Furthermore, we cache the list in-memory in the server. Currently, the
cache is not invalidated -- we may want to periodically re-list for MCP
servers. Note that they must call `list_tools` before calling
`invoke_tool` -- we use this critically.

This will enable us to list MCP servers in run.yaml

## Test Plan

Existing tests, updated tests accordingly.
2025-05-25 13:27:52 -07:00
..
agents test: add unit test to ensure all config types are instantiable (#1601) 2025-03-12 22:29:58 -07:00
datasetio chore(refact): move paginate_records fn outside of datasetio (#2137) 2025-05-12 10:56:14 -07:00
eval chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
inference fix: openai provider model id (#2229) 2025-05-22 14:51:01 -07:00
post_training fix: Pass model parameter as config name to NeMo Customizer (#2218) 2025-05-20 09:51:39 -07:00
safety feat(providers): sambanova safety provider (#2221) 2025-05-21 15:33:02 -07:00
tool_runtime fix(tools): do not index tools, only index toolgroups (#2261) 2025-05-25 13:27:52 -07:00
vector_io feat(sqlite-vec): enable keyword search for sqlite-vec (#1439) 2025-05-21 15:24:24 -04:00
__init__.py impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00