Configure DeepSeek reasoning and large-model ubatch sweep

scripts/frank-default-large.env

@@ -22,8 +22,9 @@ MTP_DRAFT_FILE=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf
 MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf
 
 # Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp
-# template drives thinking on by default (medium effort) and produces the
-# peg-native + deepseek chat/reasoning shape the Pi agent expects.
+# template drives thinking on by default (medium effort); the server emits
+# reasoning in DeepSeek format so clients receive reasoning_content separately
+# instead of literal <think> tags in content.
 CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
 CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}'
 
@@ -63,10 +64,10 @@ MIN_P=0.0
 PRESENCE_PENALTY=1.5
 
 # Reasoning on (Sharp template drives it; preserve_thinking + preserve_reasoning
-# keep the reasoning trail in the conversation). reasoning-format none lets the
-# template project the reasoning content into reasoning_content.
+# keep the reasoning trail in the conversation). DeepSeek format projects the
+# reasoning into the API's reasoning_content field instead of content tags.
 REASONING=on
-REASONING_FORMAT=none
+REASONING_FORMAT=deepseek
 
 # Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
 HSA_OVERRIDE_GFX_VERSION=11.5.1