# When a Test Fails at 3 AM: Deterministic Counterexample Repair vs. Blind Retry Loops

Published: 2026-10-18 | Domain: https://agentafk.si | Related Surface: https://agentafk.si/plan#report

## Outcome first: converging in 2 attempts instead of burning 20 blind retries

When a candidate solution fails a test at 3:00 AM during an unattended run, a naive agent harness simply appends `"Tests failed, please try again"` and samples the model again. Without a concrete counterexample, the model guesses blindly, oscillating between two broken edits until its call budget runs out. `agentafk.si` replaces blind retries with **Flight-Recorder Counterexample Self-Repair**.

## How the Flight Recorder extracts a minimal repair target

Every time `verifier.py` rejects a candidate during an overnight run, the flight recorder captures a structured failure tuple before the next turn begins:

1. **Pinpoint the violated invariant**: Identifies the exact rule ID (`rule_04_watertight_manifold` or `rule_11_no_ssrf_redirect`) that failed.
2. **Shrink the failing input**: Extracts the minimal input parameters (such as the exact vertex indices `(u=142, v=143)` with `valence == 1`, or the exact velocity vector that tunneled through collider `#3`).
3. **Lock already-passing invariants**: Instructs the repair turn that Rules 1 through 3 and 5 through 14 are already passing and must not be regressed by the patch.

```json
{
  "flight_recorder_event": "counterexample_repair_dispatch",
  "attempt_number": 2,
  "passing_rules_locked": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14],
  "failed_rule": {
    "rule_id": "rule_04_watertight_manifold",
    "open_boundary_edges_count": 12,
    "sample_unwelded_seam": {"u_xyz": [0.55, -1.1, 0.0], "v_xyz": [0.55, -1.1, -1e-7]},
    "repair_hint": "Modulo wrap final radial column i == radialSegs - 1 to column 0 instead of duplicating seam vertices"
  }
}
```

By feeding the exact unwelded seam coordinates and locking the 13 already-passing rules, `gemma4:31b` repairs the mesh generator on Attempt 2 without regressing lighting or physics.