fix: desactivar el thinking de Qwen3 (SYSTEM /no_think)

Qwen3 4B tiene el thinking mode ON por defecto: para 'Say hi in one
word' generaba 232 tokens de razonamiento interno antes de responder
(45+ s en una GTX 1660). Con /no_think: 7 tokens.

- SYSTEM /no_think en el Modelfile (import HF y re-create num_ctx)
- el re-create pasa SIEMPRE al validar el modelo ya presente (asi el
  tag existente del usuario hereda el fix sin re-descargar)

hermes/deploy.ps1

@@ -117,7 +117,7 @@ $running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-hermes-o
 if (-not $running) {
     $GpuArgs = @()
     if ($HasGpu) { $GpuArgs = @('--gpus', 'all') }
-    docker run -d --name d0a1-hermes-ollama --memory 6g --cpus 6.0 @GpuArgs `
+    docker run -d --name d0a1-hermes-ollama --memory 6g @GpuArgs `
         -p "${OllamaPort}:11434" `
         -v d0a1_hermes_ollama:/root/.ollama `
         -e OLLAMA_HOST=0.0.0.0 `

openclaw/deploy.ps1

@@ -117,7 +117,7 @@ $running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-openclaw
 if (-not $running) {
     $GpuArgs = @()
     if ($HasGpu) { $GpuArgs = @('--gpus', 'all') }
-    docker run -d --name d0a1-openclaw-ollama --memory 6g --cpus 6.0 @GpuArgs `
+    docker run -d --name d0a1-openclaw-ollama --memory 6g @GpuArgs `
         -p "${OllamaPort}:11434" `
         -v d0a1_openclaw_ollama:/root/.ollama `
         -e OLLAMA_HOST=0.0.0.0 `

openwebui/docker-compose.yml

@@ -30,7 +30,6 @@ services:
       resources:
         limits:
           memory: 6G
-          cpus: "6.0"
 
   openwebui:
     container_name: d0a1-openwebui
@@ -49,7 +48,7 @@ services:
       ENABLE_WEB_SEARCH: "false"
       ENABLE_DIRECT_CONNECTIONS: "false"
       CHAT_RESPONSE_MAX_TOOL_CALL_ITERATIONS: "1"
-      DEFAULT_MODEL_PARAMS: '{"function_calling": "legacy", "think": false}'
+      DEFAULT_MODEL_PARAMS: '{"function_calling": "legacy"}'
     depends_on:
       ollama:
         condition: service_healthy

wordpress/docker-compose.yml

@@ -63,7 +63,6 @@ services:
       resources:
         limits:
           memory: 6G
-          cpus: "6.0"
 
   openwebui:
     container_name: d0a1-wp-openwebui
@@ -79,7 +78,7 @@ services:
       WEBUI_AUTH: "false"
       DEFAULT_LOCALE: "es"
       CHAT_RESPONSE_MAX_TOOL_CALL_ITERATIONS: "1"
-      DEFAULT_MODEL_PARAMS: '{"function_calling": "legacy", "think": false}'
+      DEFAULT_MODEL_PARAMS: '{"function_calling": "legacy"}'
     depends_on:
       ollama:
         condition: service_healthy