issues group is usually where you begin.
An issue moves through six statuses, from new to fixing, review, watching, done, and ignored. It carries a severity from 1 (info) to 5 (critical) and a category that names the failure mode: tool_error, incomplete_task, wrong_tool_use, retry_storm, goal_divergence, or excessive_cost. Its evidence is the trajectories, findings, and runs behind it, plus the signals that detect it (the linked_signal_ids on the issue). The dashboard shows that evidence in three tabs, trajectories, findings, and signals, and the CLI mirrors them.
Commands
Triage an issue
List the open work, then narrow by category or severity to find what matters:linked_signal_ids and the counts behind each evidence tab:
linked_signal_ids and read the signal behind it:
Work an issue
Comment as you go:to_status is required; body is an optional note:
create requires title, summary, and category:
See also
Trajectories
The analyzed runs an issue points at.
Findings
The observations extracted from those runs.
Signals
The detectors that tie an issue together.