Development record
abcd drain run from a plain terminal stops at its first move: it reserves the first eligible issue, writes a host-judgement request, and waits for an agent session to answer it, so a person who types abcd drain in a terminal gets no fixes (seen 2026-10-22 20:47 BST on a second machine: 213 eligible, 0 lanes opened, iss-2610120138028442 reserved for 2h and left). The person wants abcd drain to work from the plain terminal by launching claude sessions itself to judge each remedy and drive each lane.
issueopenminoriss-2610222000271964
abcd drain run from a plain terminal stops at its first move: it reserves the first eligible issue, writes a host-judgement request, and waits for an agent session to answer it, so a person who types abcd drain in a terminal gets no fixes (seen 2026-10-22 20:47 BST on a second machine: 213 eligible, 0 lanes opened, iss-2610120138028442 reserved for 2h and left). The person wants abcd drain to work from the plain terminal by launching claude sessions itself to judge each remedy and drive each lane.
Grounds
- pursued: typing abcd drain in a plain terminal should work through the ledger with no host session; shown wrong if a terminal drain left for eight hours with the runner set up opens fewer lanes than a host-driven drain in the same time, for a reason other than its cap
Frontmatter
| id | iss-2610222000271964 |
|---|---|
| type | issue |
| lifecycle | open |
| severity | minor |
.abcd/work/issues/open/iss-2610222000271964-abcd-drain-run-from-a-plain-terminal.md
open on GitHub ↗ · commit history ↗
References1
- itd-2610222215485265abcd drain --drive works through the ledger from a plain terminalrelated
mentions4
- adr-2610222222326104abcd drives agents with no host session only on the person's own invocation, on the person's own account behind a wall, and hands back what it cannot finish
- dcn-26102222240407562026-10-22 — A drive asks before its first move, naming the cap, the estimated agent runs, the runner and its API key, and the answer is never remembered (facilitator, on delegation, itd-2610222215485265; revised after review round 1): asked at the first launch the question came after a reservation, which is the incident iss-2610222000271964 recorded; the default cap while driving is eight, the cap the product thinker's own drains use, and --drive --yes is the scripted yes where there is no terminal (grounds: RN2, a runner spends the person's paid key; the setup-consent rule; the 2026-10-22 recovery plan's drain at --max 8)
- iss-2610120138028442The implement loop's merged check (internal/core/implement/loop/land.go, landMerged) asks the forge twice per poll while a pull request is not merged: `gh pr view --json state`, then prMergeability's `gh pr view --json mergeable,mergeStateStatus`. Both fields come from one view, so each poll spends two forge calls where one would answer, against the same rate limit the loop's other waits share.
- itd-2610240933025076abcd plans unattended and asks only what a person owns