feat(agent): support multiple tool groups #1556
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This was referenced Mar 11, 2025
Merged
facebook-github-bot
added
the
CLA Signed
ehhuang
requested review from
SLR722,
ashwinb,
dineshyv,
dltn,
hardikjshah,
raghotham,
sixianyi0721,
terrytangyuan,
vladimirivic and
yanxi0830
as code owners
ashwinb
reviewed
Mar 13, 2025
ehhuang
added a commit
to llamastack/llama-stack-client-python
that referenced
this pull request
Mar 13, 2025
Summary: Supported by llamastack/llama-stack#1556 Test Plan: Tested in llamastack/llama-stack#1556
ashwinb
reviewed
Mar 14, 2025
ashwinb
reviewed
Mar 14, 2025
| payload=AgentTurnResponseStepStartPayload( | ||
| step_type=StepType.tool_execution.value, | ||
| step_id=step_id, | ||
| input_messages = input_messages + [message] |
There was a problem hiding this comment.
all of this code inline in this method is becoming quite hard to scan through. I think we need another file where we write some simple functions (all of these inside the agent_instance object is also a FAIL mode that I had long before initiated ever since our first agent impl lol)
ashwinb
reviewed
Mar 14, 2025
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
Outdated
Show resolved
Hide resolved
ashwinb
reviewed
Mar 14, 2025
| }, | ||
| ) as span: | ||
| tool_execution_start_time = datetime.now().astimezone().isoformat() | ||
| tool_result = await self.execute_tool_call_maybe( |
There was a problem hiding this comment.
Yes, maybe we can have a catch all and return some generic error message.
ashwinb
reviewed
Mar 14, 2025
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
Outdated
Show resolved
Hide resolved
|
Overall, I feel like there are quite a few changes to the code here and substantial ones. If we are convinced all the changed code paths are exercised by our integration tests then that's OK otherwise adding either an integration test or some kind of smaller scoped unit tests would be advisable. |
Summary: Test Plan: Summary: Test Plan: Summary: Test Plan:
Summary: Test Plan: Summary: Test Plan:
ashwinb
approved these changes
Mar 18, 2025
ehhuang
added a commit
that referenced
this pull request
Mar 18, 2025
# Summary: Includes fixes to get test_agents working with openAI model, e.g. tool parsing and message conversion # Test Plan: ``` 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/1550). * #1556 * __->__ #1550
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
closes #1488
Test Plan:
added new integration test
Stack created with Sapling. Best reviewed with ReviewStack.