todo2code

Ticket 002: Cross-repository semantic hardening

Goal and scope

Test todo2code deterministically on a fixed, reviewable corpus of external repositories, derive evidence-backed failure categories, and improve the library one measured defect at a time.

The initial corpus is:

Every repository run must use an isolated detached worktree at a recorded commit. The benchmark must not modify an external repository or consume its private and untracked files.

Acceptance criteria

Risks and mitigations

Participants

Evidence

Approval

Conclusion

Iteration 01 is accepted. It reduced false review_required findings on five external repositories without changing any graph fingerprint or gold metric. Iteration 02 fixed a tracked-evidence false positive in the generated-analysis isolation gate while retaining the original untracked-input hard negative. The next iteration should be a separate approved ticket: either broaden cross-language semantic evidence beyond the hand-written PL→EN dictionary, or sample and classify the remaining 1,853 actionable changelog findings before changing linker policy.