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Outdated suggestions cannot be applied.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.
Short Description
Adds a step to override the generated body keys in the workflow generation service to make sure the service does not give job code. Also fixes a simple bug that triggers unnecessary response regenerations when detecting empty YAML keys (see d) below).
Fixes #234
Implementation Details
a) Adds a function
override_body_keys
to replace the job codebody
key with"// Add operations here"
b) Adjusts the prompt to tell the LLM that it is not its task to generate job code. It should now refuse and tell the user they can fill it in later and refer to the Workflow Inspector AI Assistant.
I was trying to avoid fiddling with the prompt since we are working on handling job code next. However, I found it necessary to avoid a situation where the LLM claims it filled in the job code but we override it.
c) Adjusts the prompt to avoid the LLM assuming that pipe characters are needed at the beginning of body keys.
d) Fixes unnecessary response regeneration attempts when the LLM decides to give an empty YAML key by changing the key from
None
or white space" "
to an empty string""
for the regeneration attempt.AI Usage
Please disclose how you've used AI in this work (it's cool, we just want to know!):
You can read more details in our Responsible AI Policy