fix(eval): enforce pre-edit fallback route assertions - #258
Merged
Conversation
Helweg
force-pushed
the
fix/pre-edit-route-outcome-gates
branch
3 times, most recently
from
August 6, 2026 18:25
ccf374b to
4322040
Compare
Helweg
force-pushed
the
fix/pre-edit-route-outcome-gates
branch
from
August 7, 2026 00:57
4322040 to
0a1b037
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Review finding
Independent review of the three latest merged PRs found one functional omission in #257: the unresolved-symbol golden query recorded
expectedRoute: "search"andexpectedOutcome: "results", but those values were only reported as metrics. The pre-edit budget did not enforce them, so a routing regression could still pass Hit@5/MRR and CI.Fix
minRouteAccuracyandminOutcomeAccuracybudget thresholds.evaluateBudgetGate.1.0inbenchmarks/budgets/pre-edit.json.Validation
npm audit --audit-level=moderatereports 0 vulnerabilities.npm run typecheckandnpm run lintpass.npm run buildpasses. The full local test run retained four known environment-sensitive timing failures in unrelated identity/watcher tests. The changed eval suites pass in isolation and the prior merged PR checks were green.