{
  "id": "eval-harness/cost-tracking-per-run",
  "slug": "cost-tracking-per-run",
  "title": "Session: cost-tracking-per-run — 2026-11-02",
  "type": "source",
  "project": "eval-harness",
  "date": "2026-11-02",
  "started": "2026-11-02T15:25:00+00:00",
  "ended": "2026-11-02T16:25:00+00:00",
  "model": "qwen3-coder",
  "cwd": "/home/dev/code/eval-harness",
  "git_branch": "feat/cost",
  "permission_mode": "default",
  "user_messages": 1,
  "tool_calls": 3,
  "tools_used": [
    "Bash",
    "Edit",
    "Write"
  ],
  "is_subagent": false,
  "wikilinks_out": [
    "Budgets",
    "CostTracking",
    "eval-harness"
  ],
  "body_text": "Project: eval-harness · Branch: feat/cost · Mode: default · Model: qwen3-coder\n\nSummary\n\nTracked token usage and cost per eval run and per metric, with prices loaded from a versioned table, and added a budget flag that stops a run before it exceeds a limit.\n\nConversation\n\nTurn 1 — User\n\nHow much does one full eval run cost us?\n\nTurn 1 — Assistant\n\nRecord usage per judge call, price it from prices.yaml (versioned by date), aggregate per metric, and add --budget that aborts cleanly with partial results.\n\nTools used in this turn:\n\n- Edit: harness/runner.py\n- Write: harness/cost.py\n- Bash: python -m harness run suites/support.yaml --budget 5 — $3.12\n\nConnections\n\n- eval-harness\n- CostTracking\n- Budgets",
  "sha256": "aad4c6f096ec7ff6",
  "source_url": "sessions/eval-harness/2026-11-02-cost-tracking-per-run.html"
}