Update agent prompts and tools tweaks for agents #8
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
…ng, and error handling
…ent tools and must-gather implementations
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Outdated suggestions cannot be applied.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.
With this, I've noticed a lot higher success rate with getting the root agent to actually call the sub agents properly and with the right information, which happened maybe 20% of the time before. I'm even using a smaller qwen model on my local laptop, and it can still understand this better.
It seems ADK uses docstrings as well for giving more info about tools to the model: https://google.github.io/adk-docs/tools/function-tools/#docstrings, so I did that. Some of the naming for the tools was mismatched as well.
I need to test must-gather a bit more but I've received some results from it with the new tools it has.