[codex] Add aggregate constraint validation - #62
Merged
Conversation
greenthree
marked this pull request as ready for review
August 4, 2026 12:46
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 changed
T_max, aggregate work budgets, joint feasibility, and calibrationWhy
Multi-case problems can state a total-size limit without enforcing it in the Validator, or enforce a different limit than the statement. That makes the intended complexity and official data contract unreliable. This change adds a conservative automated reconciliation layer while keeping algorithmic complexity analysis and final Validator review explicitly human/Agent-owned.
User impact
Authors now receive structured aggregate-constraint diagnostics in
lintandreport. The Skill also guides authors to derive a safeT_maxand cumulative-size limit from test demand, per-case work, I/O, fixed costs, joint worst cases, and the existingaccepted_max_time * 3 <= TLcalibration rule.Validation
npm run check: 560 passed, 26 skippednpm run pack:check: probhub 213 files, probhub-skill 5 filesgit diff --checkpassedn log n, fixed per-case costs, graph limits, and joint-feasibility rejection