phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat(agent): support multiple tool groups (#1556)

Browse source 
Summary:
closes #1488 

Test Plan:
added new integration test
```
LLAMA_STACK_CONFIG=dev pytest -s -v tests/integration/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model openai/gpt-4o-mini
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1556).
* __->__ #1556
* #1550
This commit is contained in:
ehhuang 2025-03-17 22:13:09 -07:00 • committed by GitHub
parent c23a7af5d6
commit 37f155e41d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 157 additions and 108 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/inline/safety/llama_guard/llama_guard.py
View file

@ -227,13 +227,6 @@ class LlamaGuardShield:
if len(messages) >= 2 and (messages[0].role == Role.user.value and messages[1].role == Role.user.value):
messages = messages[1:]
for i in range(1, len(messages)):
if messages[i].role == messages[i - 1].role:
for i, m in enumerate(messages):
print(f"{i}: {m.role}: {m.content}")
raise ValueError(
f"Messages must alternate between user and assistant. Message {i} has the same role as message {i - 1}"
)
return messages
async def run(self, messages: List[Message]) -> RunShieldResponse: