llama-stack/llama_stack/providers/inline/agents/meta_reference
Hardik Shah 97eb3eecea
Fix Agents to support code and rag simultaneously (#908)
# What does this PR do?

Fixes a bug where agents were not working when both rag and
code-interpreter were added as tools.


## Test Plan

Added a new client_sdk test which tests for this scenario 
```
LLAMA_STACK_CONFIG=together pytest -s -v  tests/client-sdk -k 'test_rag_and_code_agent'
```

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
2025-01-30 17:09:34 -08:00
..
tests Rename builtin::memory -> builtin::rag 2025-01-22 20:22:51 -08:00
__init__.py [memory refactor][3/n] Introduce RAGToolRuntime as a specialized sub-protocol (#832) 2025-01-22 10:04:16 -08:00
agent_instance.py Fix Agents to support code and rag simultaneously (#908) 2025-01-30 17:09:34 -08:00
agents.py [memory refactor][3/n] Introduce RAGToolRuntime as a specialized sub-protocol (#832) 2025-01-22 10:04:16 -08:00
config.py Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00
persistence.py [memory refactor][5/n] Migrate all vector_io providers (#835) 2025-01-22 10:17:59 -08:00
safety.py [remove import *] clean up import *'s (#689) 2024-12-27 15:45:44 -08:00