Add support for usage limits #409
Open
+294
−48
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
Deploying pydantic-ai with
|
| Latest commit: |
3bb0e46
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://cd2f556b.pydantic-ai.pages.dev |
| Branch Preview URL: | https://usage-limits.pydantic-ai.pages.dev |
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Outdated suggestions cannot be applied.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 is an alternative implementation to #374, which uses the
Usagestruct (renamed fromCostin the base branch of this PR) to store the request count, and checks for limits to be exceeded.Relative to that PR, I changed
execution_limitsandExecutionLimitstousage_limitsandUsageLimitsrespectively. But I think everything else is mostly the same.@samuelcolvin if you don't want to rename
CosttoUsage, I would still suggest we use the approach in this PR, just change the names back.This could use more tests before merging, I wouldn't say I'm confident it is working properly in all cases yet. But I'm also not confident enough in the approach to really want to put a lot more effort into testing yet. (Though I'll note I did already add one simple test, and updated the FunctionModel and TestModel to track token counts in the usage.)