fix: describe the level as the confidence badge in the assistant prompt - #525
Merged
Merged
Conversation
|
Automatic reviews are disabled for this repository. |
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The assistant's system prompt described the project's level as an agreement label. The results screen shows that level as the confidence badge, so an answer could name something the user does not see.
Change
One paragraph of the pinned facts is reworded. In
api/assistant/agent/prompt.pythe paragraph keeps the 20 and 40 percent thresholds, says the screen shows the level as the confidence badge, and says it tells how close the mean and the median are. Every other sentence of the prompt is unchanged, and so are theagreement_levelvalues.Verification
uv run pytest tests/unit/api/assistant -n 0 -q: 978 passed. A new test intest_prompt.pyfails on the old wording../scripts/ci/ci-local.sh fast: lint clean, 3267 backend tests passed. The frontend half did not run in that tree; this change has no frontend files.Migrations
None.
Screenshots
None.