# Context Pack: run_20260430_043352_348790_risk_aware_courier_20260430_133213_robustness

## Candidate

- candidate_id: risk_aware_courier_20260430_133213
- candidate_kind: strategy
- candidate_status: champion
- status_reason: Candidate is champion on at least one layout.
- git_ref: 1efd7de193c3877789d11aa42c265a587cfb4629
- stage: robustness
- status: completed

## Overall Result

- games: 0
- win_rate: 0.0
- tie_rate: 0.0
- loss_rate: 0.0
- points_per_game: 0.0
- avg_score: 0.0
- score_std: 0.0
- error_count: 0
- timeout_count: 0
- promotion_score: 0.35

## Layout-Wise Summary

| Layout | Games | Win Rate | PPG | Avg Score | Error Rate | Timeout Rate | Promotion | Eligible | Active Rank | Champion |
|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|

## League Decision

- No league decision event recorded for this run.

## Opponent-Wise Summary

| Opponent | Games | Win Rate | PPG | Avg Score |
|---|---:|---:|---:|---:|

## Observed Weakness Heuristics

- No deterministic weakness heuristic was triggered.

## Request

```json
{
  "candidate": {
    "agent_ref": "your_best",
    "candidate_id": "risk_aware_courier_20260430_133213"
  },
  "git_ref": "1efd7de193c3877789d11aa42c265a587cfb4629",
  "layouts": [
    "defaultCapture",
    "alleyCapture",
    "mediumCapture",
    "strategicCapture",
    "bloxCapture",
    "crowdedCapture",
    "distantCapture",
    "fastCapture",
    "officeCapture",
    "RANDOM13",
    "RANDOM23",
    "RANDOM42"
  ],
  "max_workers": 12,
  "notes": "Robustness run to measure crowdedCapture-specific revision; fixed RANDOM layouts only.",
  "num_games_per_pair": 3,
  "opponent_selector": {
    "candidate_kinds": [
      "strategy"
    ],
    "eligible_statuses": [
      "promoted",
      "active",
      "champion"
    ],
    "include_baseline": true,
    "include_global_best": true,
    "mode": "layout_top_k",
    "opponents": [],
    "ranking_metric": "promotion_score",
    "top_k": 5
  },
  "run_name": "risk_aware_courier_20260430_133213_robustness",
  "stage": "robustness"
}
```

## Next Codex Task

Propose one controlled revision targeting the weakest layout or highest error/timeout source, then rerun smoke or candidate_eval as appropriate.