List agent runs

Page number for pagination (0-based, default: 0)

Number of runs per page (1-100, default: 50)

Field to sort by (default: createdAt)

Sort direction (default: desc)

Optional filter by exact agent id

Optional filter by agent name (partial match)

Optional search across execution ID, run/alert title, and agent name (partial match)

Optional comma-separated list of tool names to filter by

Optional start date filter (ISO string)

Optional end date filter (ISO string)

Optional comma-separated list of trigger source values (manual, jira, slack, etc.)

Optional JSON array of { op: gt|lt|eq|ge|le, value: number } for eval score filtering (applied as OR)

When true, only return noteworthy runs: those with critical issues, failed acceptance criteria, or high/critical severity detection hits

When true, only return runs with critical issues or failed acceptance criteria

When false, skip the exact pagination count and return zero for totalCount