fix: agents with non-llama model #1550
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
Merged
facebook-github-bot
added
the
CLA Signed
ehhuang
commented
Mar 11, 2025
Comment on lines
+996
to
1002
| if isinstance(message.content, list): | ||
| message.content.extend(contents) | ||
| else: | ||
| if isinstance(message.content, str): | ||
| message.content = [TextContentItem(text=message.content)] + contents | ||
| else: | ||
| message.content = [message.content] + contents | ||
|
|
There was a problem hiding this comment.
Append to user message instead since litellm requires tool responses message to follow a message with tool_call, which does make sense imo.
| 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}" | ||
| ) |
There was a problem hiding this comment.
removing this check as OpenAI models can output multiple tool calls
ehhuang
changed the title
ehhuang
requested review from
SLR722,
ashwinb,
dineshyv,
dltn,
hardikjshah,
raghotham,
sixianyi0721,
terrytangyuan,
vladimirivic and
yanxi0830
as code owners
ashwinb
reviewed
Mar 12, 2025
ehhuang
commented
Mar 12, 2025
Closed
ehhuang
force-pushed
the
pr1550
branch
2 times, most recently
from
b1acc52 to
9700ce6
Compare
ashwinb
approved these changes
Mar 17, 2025
ehhuang
force-pushed
the
pr1550
branch
3 times, most recently
from
b6ed0c5 to
87a2a56
Compare
Summary: Test Plan: Summary: Test Plan: Summary: Test Plan:
ehhuang
added a commit
that referenced
this pull request
Mar 18, 2025
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
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:
Includes fixes to get test_agents working with openAI model, e.g. tool parsing and message conversion
Test Plan:
Stack created with Sapling. Best reviewed with ReviewStack.