Allow specification of maximum event contents in prompt to mitigate error compounding #154
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
…ate error compounding
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
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Outdated suggestions cannot be applied.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.
This PR allows specification of max_contents in an LlmAgent. Currently, the system prompt given to an agent will include its entire event history so that it can reference past content from the conversation, tool calls, etc. The problem is that if occasionally the agent hallucinates or even the user introduces bad content, this will remain in history and potentially lead to compounding error. For some applications where interactions with the agent are expected to be of a certain reasonable range of length, it can be beneficial to set max_contents accordingly, but this PR leaves it None (unlimited) by default. This configuration is related to include_contents which can be set to 'none' to disable historical content in the prompt altogether.