submission.yaml

submission_id: 2026-06-01__001_synthetic_mine_throughput__claude-code__claude-opus-4-8__plan-mode-max-effort
date: 2026-06-01
benchmark_id: 001_synthetic_mine_throughput
harness:
  name: claude-code
  version: tbc
  notes: plan mode, max effort
model:
  name: claude-opus-4-8
  vendor: anthropic
  notes: max effort thinking
run_tag: plan-mode-max-effort
operator: harry
status: complete
intervention:
  category: plan-mode
  notes: >-
    Built in Claude Code plan mode (max effort). Implemented src/mine_sim as a
    SimPy discrete-event model adapted from the prior opus-4-7
    ouroboros-max-thinking submission, with a corrected LOCKED FLAT summary.json
    schema (per-scenario total_tonnes_mean / tonnes_per_hour_mean), flat outputs
    to the submission root, --event-log-scope first default, the optional 7th
    combo scenario (trucks_12_ramp_upgrade), a focused 78-test pytest suite, and
    data-derived topology.png + animation.gif. Automated harness checks: 57/57.