Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Collaborator
|
Could you clarify |
Contributor
Author
|
|
For streaming tools, make the `result` be the final aggregation snapshot, and then have a separate `model_result`. This allows the `result` of a subagent to be the full `MessageBundle`, which has the advantage that the `preliminary` type when streaming over the ai-sdk ui matches the final type. UIMessage <-> MessageBundle coversions are done on the ai-sdk ui side, and we now pass tools in to enable that.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
For streaming tools, make the
resultbe the final aggregationsnapshot. This allows the
resultof a subagent to be the fullMessageBundle, which has the advantage that thepreliminarytype when streaming over the ai-sdk ui matches the final type.
We add a hidden
_model_inputto messages representing the actualvalue to be sent to the model. This gets set on
ToolResultPartwhenon tool completion and by
Agent.runwhen processing messages thatare missing them.
We do it this way because
Agent.runhas access to the tools.