Repository navigation
schemathesis_datagen_pipeline: state the Target 1 module interface - #54
Draft
findalexli wants to merge 1 commit into
Draft
findalexli wants to merge 1 commit into
findalexli wants to merge 1 commit into
Conversation
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Task finding: #49.
What and why
Hidden Phase 1 imports names from
schemathesis.specs.openapi.headersand checks literal format keys and Range forms thatTODO.mddoesn't give. A module with other names fails the import and loses all of Phase 1, 15.38 of 100 points. This PR adds a "Target 1 Module Interface" section toinstruction.mdand adjusts one rule line to allow it.It goes in
instruction.mdbecauseenvironment/DockerfilepinsTODO.mdto v1's commit. Putting it inTODO.mdwould mean updating the pin and accepting new image tags.Old vs new judge
Both trees build the same images: judge
484f15fd657f, work8911231cbfba; 18 of 18 files underenvironment/andjudge/have the same sha256. One worker,tools/judge_local.py, task limits. "Names" is an alias layer we added to the real archive, standing in for a solver told them; we didn't measure how a solver reacts to this text.headers.pyfrom Schemathesis 4.15.0The spread in the second row is an existing unseeded test (below), not the patch. Over all six jobs on this image: 72.31 in 19 of 19 grades, 85.64 or 86.67 in 15, 87.69 in 13, 47.73 in 11 of 12 (46.71 once).
In the public rollouts at
huggingface.co/datasets/adafadaq/edgebench-opus-5-5-xhigh-rollouts, all 96 graded Kimi K3 and Qwen 3.5 submissions score 0 of Phase 1. We didn't check each one's cause.Not in this PR.
test_negative_mode_range_has_three_tiersneeds the exact valuebytes=among 200 unseeded examples, so one file can lose 1.03 points on one grade.HTTP_DATE_REaccepts impossible dates. Fixing either can move scores, so each needs its own PR. Details: https://github.com/findalexli/EdgeBench/tree/da540564098c8bbc0ad5b9b4cfce0ce53045f8d6/schemathesis_datagen_pipeline.Checklist for task changes
versionintask.tomlis bumped.NOTES.md: the change is under Changes; Source notes the instruction change. It isn't a listed Known issue.