{% extends "_base.html" %} {% block title %}harness-evaluator — {{ run_name }} — {{ cell.cell_id }}{% endblock %} {% block content %}
| Input | Output | Cache Read | Cache Write | Reasoning | Total |
|---|---|---|---|---|---|
| {{ cell.input_tokens }} | {{ cell.output_tokens }} | {{ cell.cache_read_tokens }} | {{ cell.cache_write_tokens }} | {{ cell.reasoning_tokens }} | {{ cell.input_tokens + cell.output_tokens + cell.cache_read_tokens + cell.cache_write_tokens + cell.reasoning_tokens }} |
| API Calls | Tool Calls | Time to First Attempt |
|---|---|---|
| {{ cell.num_api_calls }} | {{ cell.num_tool_calls }} | {{ "%.1f"|format(cell.time_to_first_attempt_ms / 1000) }}s |
Error Class: {{ cell.error_class }}
{% endif %} {% if cell.error_message %}{{ cell.error_message }}{% endif %}
{{ cell.diff }}
{{ cell.test_output }}
{{ cell.harness_metadata }}
| Phase | Model | Role | Exit Code | Duration | Input Tokens | Output Tokens | Cost | API Calls | Timed Out |
|---|---|---|---|---|---|---|---|---|---|
| {{ p.phase_name }} | {{ p.model }} | {{ p.model_role }} | {{ p.exit_code }} | {{ "%.1f"|format(p.duration_ms / 1000) }}s | {{ p.input_tokens }} | {{ p.output_tokens }} | ${{ "%.6f"|format(p.total_cost) }} | {{ p.num_api_calls }} | {{ "yes" if p.timed_out else "no" }} |
Matched: {{ "yes" if reconciliation.matched else "no" }}
Max Discrepancy: {{ "%.1f"|format(reconciliation.max_discrepancy_pct) }}%
{% if reconciliation.proxy_usage_json %}Proxy Usage:
{{ reconciliation.proxy_usage_json }}{% endif %}
{% if reconciliation.self_reported_usage_json %}Self-Reported Usage:
{{ reconciliation.self_reported_usage_json }}{% endif %}
{% if reconciliation.details_json %}Details:
{{ reconciliation.details_json }}{% endif %}