← older: fast__qwen3.6-35b-a3b__20260706-230157all runs · task boardnewer: fast__qwen3.6-35b-a3b__20260707-001626 →

fastqwen3.6-27b20260706-231402

No notes for this run yet. Add runs/fast__qwen3.6-27b__20260706-231402/NOTES.md — what was run & what changed, results, interpretation, next steps — and it will render here.

Run details

modelllama-local/qwen3.6-27bagentharnesses.subagents_pi:SubagentsPithinkingonreasoning budgetdirect (server/none)* — see journal for the authoritative mechanismmaxTokens / contextWindow65536 / 196608agent timeout ×2.0trials9 of 9 — 6 pass · 3 failmean reward0.67tokens (job total)2,856,712 in / 64,696 outstarted / finished2026-07-06T23:14 / 2026-07-07T00:16wall clock1h02m

Tasks

cancel-async-tasks — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	2m12s	1m20s	95588/3828	—	🔍 view

filter-js-from-html — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	8m47s	5m24s	555563/12462	—	🔍 view

fix-git — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	1m17s	38s	83322/1387	—	🔍 view

nginx-request-logging — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	5m10s	4m30s	111334/2606	—	🔍 view

openssl-selfsigned-cert — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	1m58s	1m19s	170516/3525	claimed success but the verifier did NOT pass (heuristic)	🔍 view

query-optimize — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	16m12s	9m30s	145381/2825	—	🔍 view

regex-log — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	8m06s	7m17s	283525/19135	long reasoning (18,695 chars)	🔍 view

sanitize-git-repo — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	10m13s	9m33s	150574/3911	—	🔍 view

sparql-university — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	8m23s	7m36s	1260909/15017	a bash command timed outlong reasoning (21,807 chars)	🔍 view