diff --git a/tools/lanes/drafter.sh b/tools/lanes/drafter.sh
index 02dfe7770..01ed9befe 100644
--- a/tools/lanes/drafter.sh
+++ b/tools/lanes/drafter.sh
@@ -79,6 +79,16 @@
 # larger output budget costs latency and nothing else.
 set -u
 cd /home/musashi/bfm-decomp
+# HTTP_TIMEOUT 700 (P31 S59) — MUST be raised WITH MAXTOK; they are one setting, not two.
+# Measured on ox-alpha with a real MIPS derivation: 30 tok/s, and an UNCAPPED hard prompt ran
+# 265 s for 8,067 completion tokens — i.e. it wanted to finish exactly where the old 8k cap cut it
+# off, which is the nudge storm we were seeing. At 30 tok/s a full 16k generation needs ~530 s, so
+# leaving the socket at 420 s would have killed the very turns the bigger budget exists to allow —
+# and a timeout wastes the whole turn, where truncation at least leaves a partial.
+# The ordering that must hold: generation < HTTP_TIMEOUT (700) < stallguard's wedged-agent kill
+# (1200 s). 420 was itself a deliberate choice after 1800 parked a hung agent for THIRTY minutes;
+# this keeps that concern (a hang costs <12 min) without strangling legitimate deep reasoning.
+export HTTP_TIMEOUT=700
 export MAX_429=10
 while [ ! -e .run/ox_campaign.stop ]; do
   .venv/bin/python tools/ox_campaign.py --drafter \
diff --git a/tools/lanes/main.sh b/tools/lanes/main.sh
index e5da9d67b..fedd00427 100644
--- a/tools/lanes/main.sh
+++ b/tools/lanes/main.sh
@@ -13,6 +13,16 @@
 # excluded — already drafted, never gated, free), then draws and drafts its own main cards.
 set -u
 cd /home/musashi/bfm-decomp
+# HTTP_TIMEOUT 700 (P31 S59) — MUST be raised WITH MAXTOK; they are one setting, not two.
+# Measured on ox-alpha with a real MIPS derivation: 30 tok/s, and an UNCAPPED hard prompt ran
+# 265 s for 8,067 completion tokens — i.e. it wanted to finish exactly where the old 8k cap cut it
+# off, which is the nudge storm we were seeing. At 30 tok/s a full 16k generation needs ~530 s, so
+# leaving the socket at 420 s would have killed the very turns the bigger budget exists to allow —
+# and a timeout wastes the whole turn, where truncation at least leaves a partial.
+# The ordering that must hold: generation < HTTP_TIMEOUT (700) < stallguard's wedged-agent kill
+# (1200 s). 420 was itself a deliberate choice after 1800 parked a hung agent for THIRTY minutes;
+# this keeps that concern (a hang costs <12 min) without strangling legitimate deep reasoning.
+export HTTP_TIMEOUT=700
 while [ ! -e .run/ox_campaign.stop ]; do
   .venv/bin/python tools/main_lane.py --workers 150 --batch 40 --cards 200 --max-ins 200 --maxtok 16000 2>&1
   echo "[$(date +%H:%M:%S)] [main-lane] exited; restarting in 20s"