Comparison
Test setup, rules and sandboxing
Findings about how the tests themselves are run: written rules, changes to the test harness, and sandbox tools that confine the agent.
Comparison · site/content/finding-pages.json
Findings about how the tests themselves are run: written rules, changes to the test harness, and sandbox tools that confine the agent.
Results, newest first
| Result | Verdict | Finished |
|---|---|---|
| Approval delays lack phase attribution | Unresolved | 8 November 2026 |
| Alarm relays to main: one line per event removes every repeat | Yes | 5 November 2026 |
| Rule: loop-vs-Codex time and cost are measured only on the two Linux servers | Yes | 30 October 2026 |
| Test harness change: install dependencies once, retry timed-out approvals | Yes | 30 October 2026 |
| Why a Kogen approval timed out: the shared 120-second deadline under heavy load | Yes | 30 October 2026 |
| Four macOS sandbox tools measured against Kogen's old containment needs (historical) | Yes | 15 October 2026 |