The whole retired engine at once: every config switch, raw ERP data, locks, and pins.
- Version
- Category
- software-engineering
- Difficulty
- expert
- Model configurations
- 3
- Attempts
- 16
- Public trials
- 161 passed
- Median runtime
- 8m 53s
Instruction
# Rebuild the whole retired engine The old planning module was retired last quarter and its allocation engine's source did not survive the migration. Its captured production runs are in `audit/` — request/plan pairs, exactly as the engine consumed and produced them. The decision policy was never written down; the archive is the only spec. The live engine never saw switches one at a time. This is a full production cycle: four campuses, a raw ERP extract, supplier pins, `enforceSingleSupplier`, and a locked phase at ALB01 with committed assignments in the request. Implement the engine at `allocator/solve.py` (entry point in `allocator/README.md`) so it reproduces the legacy engine's planning behavior on any request, and use it to plan `data/scenario.json`. The engine re-runs as the world changes — new lots land and phases lock between runs — and grading is outcome equivalence with the legacy engine, not matching its exact lot choices. Check plan structure with `python3 contracts/validate.py <request.json> <response.json>`.
Public trials
Results by model
| Model · harness | Mean reward | Range | ± SE | Attempts |
|---|---|---|---|---|
| Muse Spark 1.3 ContributorOpenCode | 56.5% | 0% – 100% | 9.1 pp | 11 |
| gemini-3.1-pro-previewOpenCode | 39.0% | 39% – 39% | 0.0 pp | 2 |
| GPT 5.6 SolOpenCode | 39.0% | 0% – 78% | 22.5 pp | 3 |