{% extends "ui/base_ui.html" %} {% block title %}Eval Run — {{ agent_name }} / {{ suite_name }} - ATP Platform{% endblock %} {% block content %}
Latest run {{ run.run_uuid }} ·
critical_pass_rate
{{ "%.3f"|format(run.critical_pass_rate) if run.critical_pass_rate is not none else "—" }}
· breakpoint {{ run.breakpoint_axis_level or "—" }}
No completed run found for {{ agent_name }} on
{{ suite_name }} yet.
No per-case detail for this run (aggregate-only import — re-run the sweep with
the current harness to capture case_details).
| axis_level | cases | critical_pass | pass_rate |
|---|---|---|---|
| {{ a.axis_level }} | {{ a.n }} | {{ a.critical_pass }} | {{ "%.3f"|format(a.pass_rate) }} |
| case_id | axis_level | critical_pass | malformed | recall | precision | fp_count |
|---|---|---|---|---|---|---|
| {{ c.case_id }} | {{ c.axis_level or "—" }} | {{ "✓" if c.critical_pass else "✗" }} | {{ "✓" if c.malformed else "" }} | {{ "%.3f"|format(c.recall) if c.recall is not none else "—" }} | {{ "%.3f"|format(c.precision) if c.precision is not none else "—" }} | {{ c.fp_count if c.fp_count is not none else "—" }} |