2026-10-16 — Agents keep running past the host's permission prompts in two ways (product thinker, 2026-10-16): abcd teaches agents the command forms the host can check (iss-2610161612200864), and, for the agents abcd itself starts without a terminal, abcd answers the prompts per launch with its guard rules (iss-2610161612203555). abcd does not approve commands in interactive sessions, does not sandbox, and never edits the person's host settings.

Frontmatter

.abcd/work/decisions/dcn-2610161612269647-agents-keep-running-past-the-host-s.md
open on GitHub ↗ · commit history ↗

mentions5

• adr-2610161621415708Unattended runs abcd launches execute inside an OS sandbox
• dcn-26101616192966152026-10-16 — Correction to dcn-2610161612269647: sandboxing autonomous runs was not declined. The 2026-10-16 question offered only teaching and per-launch approvals, after the sandbox option was dropped to fit the screen, so the product thinker made no ruling on it; it stays open, and the product thinker named it on the same day as an important feature for autonomous runs.
• iss-2610161612200864Agents stall at the host's permission prompt when they write a command the host cannot check. On 2026-10-16 a background agent ran a bash -c script built from variables that deleted files. The host could not check it, so it asked 'This shell -c script runs rm and could not be checked. Do you want to proceed?', and the agent waited for a person. No bundled rule teaches the forms the host can check.
• iss-2610161612203555An agent abcd starts without a terminal has nobody to answer the host's permission prompts. A command the host cannot check is then refused, and the lane stalls or fails. The product thinker chose to have abcd answer those prompts for the agents it starts, using its existing guard rules.
• itd-2610161621364075The agents abcd launches on its own work inside a sandbox the operating system enforces