fix(e2e): allow dynamic multi-turn tool retries#173
Open
BlackishGreen33 wants to merge 1 commit into
Open
Conversation
Signed-off-by: 墨綠BG <s5460703@gmail.com>
|
@BlackishGreen33 is attempting to deploy a commit to the Vercel Team on Vercel. A member of the Team first needs to authorize it. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
The
dynamic-tools/multi-turneval no longer requires exactly two matchingecho_dynamictool calls across the whole run.The eval already checks the important behavior inside each turn:
echo_dynamicand getsdynamic-echo-ok-X7R2echo_dynamicafter session serialization and gets the same tokenThis fixes a valid retry case where the model calls the turn two tool more than once. In that case, the dynamic tool is still working, but the old run-wide
times: 2assertion fails because it sees three successful calls.Closes #122.
How
Removed the final run-wide
t.calledTool(ECHO_TOOL, { ..., times: 2 })assertion fromdynamic-tools/multi-turn.The per-turn
requireToolOutput(...)checks stay in place, so the eval still verifies that the dynamic tool survives across turns and returns the expected token each time.Tests / changeset
evepackage behavior.Verification
fnm exec --using v24.15.0 pnpm typecheckfnm exec --using v24.15.0 pnpm fmtfnm exec --using v24.15.0 pnpm lintfnm exec --using v24.15.0 pnpm buildgit diff --check