Development preview

Faber Proof

Codex can write the patch. Faber makes the patch prove itself.

Faber turns a patch’s requirements into falsifiable obligations, runs only repository-approved checks, and returns an evidence-bound PASS, BLOCK, or HUMAN_REVIEW decision.

Development replay comparison: ordinary tests pass for both patches, while Faber Proof blocks the bad patch and passes the repaired patch — Deterministic local replay using a development fixture (`REPLAY — FAKE-DEVELOPMENT`); not live-model or production evidence.

Method

A proof path with explicit authority.

Plan

Turn task requirements and a bounded diff into claims that can be tested.

Check

Execute only evidence capabilities approved by repository policy.

Decide

Bind results to the exact patch and return an auditable decision.

Trust boundary

Evidence, not model prose, decides.

The planner can identify claims and select approved proof templates. It cannot provide arbitrary commands or the final verdict.

Missing, contradictory, or unbound evidence CANNOT PASS

Authoritative evidence disproves a requirement BLOCK

Policy requires human judgment HUMAN_REVIEW

All required evidence is valid and passing PASS

Current scope

Local, reproducible, deliberately bounded.

Faber Proof is currently a development-local tool. Its no-key replay path can reproduce evidence reports without an account or network request. The local runner is not a production sandbox, and a passing report covers declared obligations—not universal correctness.