-
Notifications
You must be signed in to change notification settings - Fork 1.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(product-assistant): a human in the loop for the taxonomy agent #26767
Conversation
…thog into feat/agent-human-in-the-loop
|
||
class Conversation(UUIDModel): | ||
user = models.ForeignKey(User, on_delete=models.CASCADE) | ||
team = models.ForeignKey(Team, on_delete=models.CASCADE) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Now, I think that there should be a ref to the project because property values can differ. @Twixes what do you think?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We can't really have a meaningful analysis shared between environments because of data differing, so team-level (aka environment-level) is the right way here
📸 UI snapshots have been updated10 snapshot changes in total. 0 added, 10 modified, 0 deleted:
Triggered by this commit. |
…thog into feat/agent-human-in-the-loop
The CI fails because there is a bug in migrations tests, which I've fixed in #26928. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A mammoth PR so I might have missed something, but overall looks good, with a few comments!
|
||
class Conversation(UUIDModel): | ||
user = models.ForeignKey(User, on_delete=models.CASCADE) | ||
team = models.ForeignKey(Team, on_delete=models.CASCADE) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We can't really have a meaningful analysis shared between environments because of data differing, so team-level (aka environment-level) is the right way here
frontend/__snapshots__/scenes-app-max-ai--welcome-loading-suggestions--dark.png
Outdated
Show resolved
Hide resolved
…thog into feat/agent-human-in-the-loop
📸 UI snapshots have been updated2 snapshot changes in total. 0 added, 2 modified, 0 deleted:
Triggered by this commit. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's get this in
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not important to shipping, but could be useful in terms of maintainability: Would it make sense to split this out into its own PyPI package, langgraph_checkpoint_django
? This part seems pretty much abstract, independent from PostHog specifics, could be useful for others building on Django too
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's get this in
|
Suspect IssuesThis pull request was deployed and Sentry observed the following issues:
Did you find this useful? React with a 👍 or 👎 |
Problem
If the request is ambiguous or the taxonomy doesn't provide a clear picture, we should ask the user to clarify their request.
Demo
Changes
Further work:
Does this work well for both Cloud and self-hosted?
No
How did you test this code?
Manual testing, Storybook, more unit tests.