feat: Add agent tools to completion data before sending to litellm in prompt #498
Conversation
This file contains 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
Signed-off-by: Diwank Singh Tomer <[email protected]>
Signed-off-by: Diwank Singh Tomer <[email protected]>
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
There was a problem hiding this comment.
❌ Changes requested. Reviewed everything up to ed3b27a in 30 seconds
More details
- Looked at
353lines of code in14files - Skipped
0files when reviewing. - Skipped posting
3drafted comments based on config settings.
1. agents-api/agents_api/activities/task_steps/raise_complete_async.py:29
- Draft comment:
Debugging print statements should be removed or replaced with proper logging before merging the code. - Reason this comment was not posted:
Marked as duplicate.
2. agents-api/agents_api/routers/tasks/update_execution.py:46
- Draft comment:
Debugging print statements should be removed or replaced with proper logging before merging the code. - Reason this comment was not posted:
Marked as duplicate.
3. agents-api/tests/test_execution_workflow.py:482
- Draft comment:
Consider reducing the sleep duration to speed up test execution unless the delay is necessary for the test logic. - Reason this comment was not posted:
Confidence changes required:50%
The sleep duration in tests should be minimized to reduce test execution time unless necessary for the test logic.
Workflow ID: wflow_wYI2Nf85Yx5cyqmd
Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.
There was a problem hiding this comment.
👍 Looks good to me! Incremental review on 06666ee in 17 seconds
More details
- Looked at
13lines of code in1files - Skipped
0files when reviewing. - Skipped posting
1drafted comments based on config settings.
1. agents-api/agents_api/activities/task_steps/prompt_step.py:74
- Draft comment:
Consider adding error handling for thelitellm.acompletioncall to manage potential exceptions and ensure robustness. - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable:
The comment is about a potential improvement in error handling for a function call that is part of the changed code. Although the change itself was the removal of print statements, the suggestion for error handling is relevant to the robustness of the code. The comment is actionable and clear, suggesting a specific improvement.
The comment might be considered speculative since it assumes there could be exceptions without evidence. However, error handling is generally a good practice, especially for asynchronous calls.
Even though the comment is somewhat speculative, adding error handling is a common practice to improve code robustness, especially for network or I/O operations.
Keep the comment as it suggests a clear and actionable improvement related to the changed code.
Workflow ID: wflow_qTdOc9PIHfCax7Rc
You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.
HamadaSalhab
deleted the
SCRUM-15-agents-api-Implement-prompt-step-if-tool_calls
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
feat: Add agent tools to completion data and update transition logic
Summary:
Adds agent tools to completion data and updates transition logic across the codebase.
Key points:
prompt_step.py, updates task token handling inraise_complete_async.py, and refactors transition logic intransition_step.py.task_tokentoCreateTransitionRequestinopenapi_model.py.tasks.py.test_execution_workflow.pyfor new workflow steps..DS_Storefiles (should be removed).Generated with ❤️ by ellipsis.dev