feat: include assertions and pass@k in baseline regression comparison - #4103
Merged
Conversation
melmennaoui
force-pushed
the
feat/4087-baseline-assertions-passk
branch
from
September 1, 2026 15:57
47ac4f6 to
54f6b49
Compare
Extend the baseline regression gate to cover assertion pass rates and surface pass@k/pass^k consistency metrics from --repeat runs. Also removes the verify script dead code (verify field, VerifyCheck type, verify.go/verify_test.go) — the assertion system covers verifiable cases via the captured event stream, and verify cannot work without container lifecycle changes that aren't warranted. Assertion rate gates: - AssertionRate added to Metrics, derived from Summary totals - Compare() gates on assertion rate drops (same semantics as size and relevance) - computeSummary() accumulates assertion counts - printSummary() displays the Assertions metric line Repeat metrics (informational): - PassK, HatK, RepeatK added to Metrics - Compare() reports pass@k and pass^k as informational deltas Verify cleanup: - Removed EvalCriteria.Verify, VerifyCheck, verify.go, verify_test.go - Schema's DisallowUnknownFields ensures clean future re-addition Closes #4087
aheritier
added
kind/feat
melmennaoui
force-pushed
the
feat/4087-baseline-assertions-passk
branch
from
September 1, 2026 16:01
54f6b49 to
c90793b
Compare
aheritier
added
the
area/testing
dgageot
approved these changes
Sep 1, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Extend the baseline regression gate to cover assertion pass rates and surface pass@k/pass^k consistency metrics from
--repeatruns. Also removes the verify script dead code — the assertion system covers verifiable cases via the captured event stream.Changes
Assertion rate gating (
baseline.go)AssertionRate/HasAssertionsadded toMetricsmetricsOfSummary()populates assertion rate fromSummarytotalsCompare()gates on assertion rate drops — same semantics as size and relevanceRepeat metrics — informational (
baseline.go)PassK,HatK,RepeatK,HasRepeatadded toMetricsCompare()reportspass@kandpass^kas informational deltas (non-gating — they derive from the same per-eval pass/fail that individual eval changes already gate on)Summary accumulation (
types.go,scoring.go)AssertionsPassed/AssertionsTotaladded toSummarycomputeSummary()accumulates assertion countsprintSummary()displays the Assertions lineVerify cleanup
The verify concept (shell script via
docker execpost-agent) cannot work without container lifecycle changes: the container uses--rmand exits before verify could run. Assertions cover the verifiable cases via the captured event stream.Removed:
EvalCriteria.Verify,VerifyChecktype,verify.go,verify_test.go, clone and test references.Tests
TestCompare_AssertionRateDropRegressesTestCompare_AssertionRateNoDropIsCleanTestMetricsOf_AssertionsFlagTestMetricsOf_RepeatMetricsPopulatedTestCompare_PassKIsInformationalTestComputeSummary_AssertionsCloses #4087