← older: fast2__qwen3.6-27b__20260709-085257all runs · task boardnewer: fast2__qwen3.6-27b__20260709-102302 →

fast2qwen3.6-27b20260709-093420

No notes for this run yet. Add runs/fast2__qwen3.6-27b__20260709-093420/NOTES.md — what was run & what changed, results, interpretation, next steps — and it will render here.

Run details

modelllama-local/qwen3.6-27bagentharnesses.plan_pi:PlanPithinkingonreasoning budgetdirect (server/none)* — see journal for the authoritative mechanismmaxTokens / contextWindow65536 / 196608agent timeout ×2.0trials6 of 6 — 4 pass · 2 failmean reward0.67tokens (job total)4,282,361 in / 69,763 outstarted / finished2026-07-09T09:34 / 2026-07-09T10:23wall clock48m39s

Tasks

financial-document-processor — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	4m01s	3m06s	145365/7464	—	🔍 view

fix-ocaml-gc — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	21m50s	14m57s	1974342/21544	long reasoning (31,614 chars) ×2	🔍 view

git-multibranch — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	2m46s	1m57s	240460/5754	claimed success but the verifier did NOT pass (heuristic)	🔍 view

headless-terminal — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	5m18s	4m26s	274948/10406	a bash command timed out	🔍 view

mailman — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	8m04s	7m05s	1525602/13181	a bash command timed out	🔍 view

reshard-c4-data — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	6m38s	5m00s	121644/11414	fast-timeout cut at 5mlong reasoning (22,500 chars)	🔍 view