browser subagents run synchronously, hit the 40-step cap, and the apply quota counts sessions: 76 min idle or improvising in run 172 #381
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
What happens
In run 172's
openspec.apply[all]the agent made sixbrowsersubagent calls (238, 162, 147, 350, 967 and 503 s); every one ended with "Maximum steps reached", and the main agent sat idle for each (a 980 s step at 09:49:47). The seventh call was refused: the step "has had 4 browser checks". The quota counted sessions, not calls, and bit after six. With nothing telling it to stop verifying, the agent then spent 10:02-10:33 writing its own Playwright harness: three race bugs in the harness, tensleeppolls from 5 to 280 s (about 14 min asleep). The judge rounds show the same cap: 25 browser subagents over three rounds, 4-5 hit the cap and needed a continuation brief of 2-5k chars written by the slow main model ("Finish check 2 (free retry)"), and a respawn resets the quota (r3 used 10).Fix
browserrun withbackground: trueliketest, so the main agent keeps working.find/tabs/screenshotcalls, or raise it to ~60.Done when
An apply step's browser checks finish in the background, a pass is not cut mid-check, and a spent quota ends verification instead of starting a hand-written harness. ~45 + 31 min on run 172.
From the run 172 transcript review (Scratch on vLLM + MTP k=4, 2026-11-04; report in the owner's
~/repos/vLLM/reports/). Related: braid#378, braid#379.Shipped in PR #390, production
ddd4b6b.browserin the background.Measured on run 172:
browseralready offeredbackground: true, but the brief said it only oftest. All 24 calls in apply and rounds 2 and 3 ran in the foreground. Apply's onetestcall did use the background.Evidence:
tests/engine/test_browser_delegation.py, and simsbrowser-checks-cappedandbrowser-check-out-of-turns.Staying open: no model has been seen using the background. A Free run has no
browsersubagent, since its primary drives the browser itself, so a Free replay cannot show it. A Free replay of run 172's apply confirmed that: it succeeded in 17.4 minutes with no subagent calls. trogdor was busy elsewhere.Done when: on a vLLM run, apply's
browsercalls carrybackground: trueand the step keeps working while they run.Shown on a Free replay of run 172's
openspec.apply[all], on the build of PR #400 (braid#399 gives a Free run abrowsersubagent on its judge tier):browsersubagent<subagent state="completed">message, which is the background path, not a tool resultThe remaining step was "on a vLLM run, apply's
browsercalls carrybackground: trueand the step keeps working". The Free replay shows the same brief doing that. Closing once #400 merges.Closing on the Free replay above: with PR #400 merged (
2b6f451b), a Free run's apply startsbrowserin the background and keeps working. The next vLLM run is the soak test.