fix: limite de CPU 6.0 para ollama

803% de CPU durante el thinking (ya fixeado con think=false) podria
repetirse en cargas largas. Cap de 6 CPUs (de las 8+ del host):
- compose (openwebui/wordpress): deploy.resources.limits.cpus: 6.0
- docker run (hermes/openclaw): --cpus 6.0

Verificado: cap de 3.5 en host de 4 cores => 353% max (cap respetado).

hermes/deploy.ps1

@@ -117,7 +117,7 @@ $running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-hermes-o
 if (-not $running) {
     $GpuArgs = @()
     if ($HasGpu) { $GpuArgs = @('--gpus', 'all') }
-    docker run -d --name d0a1-hermes-ollama --memory 6g @GpuArgs `
+    docker run -d --name d0a1-hermes-ollama --memory 6g --cpus 6.0 @GpuArgs `
         -p "${OllamaPort}:11434" `
         -v d0a1_hermes_ollama:/root/.ollama `
         -e OLLAMA_HOST=0.0.0.0 `
@@ -147,6 +147,7 @@ if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e'
 $ModelList = docker exec d0a1-hermes-ollama ollama list 2>$null
 if ("$ModelList" -match 'qwen3:4b') {
     Info 'Modelo qwen3:4b ya descargado (volumen intacto). Omitiendo descarga.'
+    cmd /c docker exec d0a1-hermes-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf' '>' NUL '2>&1'
 } else {
     # --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
 
@@ -165,7 +166,7 @@ foreach ($Url in $HfUrls) {
 if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     Info 'Importando modelo en Ollama...'
     docker cp "$Gguf" d0a1-hermes-ollama:/root/.ollama/import.gguf
-    docker exec d0a1-hermes-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+    docker exec d0a1-hermes-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     $CreateOk = ($LASTEXITCODE -eq 0)
     docker exec d0a1-hermes-ollama rm -f /root/.ollama/import.gguf | Out-Null
     Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
@@ -178,7 +179,7 @@ if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     if ($LASTEXITCODE -eq 0) {
         $PullOk = $true
         # Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
-        docker exec d0a1-hermes-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+        docker exec d0a1-hermes-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

openclaw/deploy.ps1

@@ -117,7 +117,7 @@ $running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-openclaw
 if (-not $running) {
     $GpuArgs = @()
     if ($HasGpu) { $GpuArgs = @('--gpus', 'all') }
-    docker run -d --name d0a1-openclaw-ollama --memory 6g @GpuArgs `
+    docker run -d --name d0a1-openclaw-ollama --memory 6g --cpus 6.0 @GpuArgs `
         -p "${OllamaPort}:11434" `
         -v d0a1_openclaw_ollama:/root/.ollama `
         -e OLLAMA_HOST=0.0.0.0 `
@@ -147,6 +147,7 @@ if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e'
 $ModelList = docker exec d0a1-openclaw-ollama ollama list 2>$null
 if ("$ModelList" -match 'qwen3:4b') {
     Info 'Modelo qwen3:4b ya descargado (volumen intacto). Omitiendo descarga.'
+    cmd /c docker exec d0a1-openclaw-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf' '>' NUL '2>&1'
 } else {
     # --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
 
@@ -165,7 +166,7 @@ foreach ($Url in $HfUrls) {
 if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     Info 'Importando modelo en Ollama...'
     docker cp "$Gguf" d0a1-openclaw-ollama:/root/.ollama/import.gguf
-    docker exec d0a1-openclaw-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+    docker exec d0a1-openclaw-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     $CreateOk = ($LASTEXITCODE -eq 0)
     docker exec d0a1-openclaw-ollama rm -f /root/.ollama/import.gguf | Out-Null
     Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
@@ -178,7 +179,7 @@ if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     if ($LASTEXITCODE -eq 0) {
         $PullOk = $true
         # Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
-        docker exec d0a1-openclaw-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+        docker exec d0a1-openclaw-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

openwebui/deploy.ps1

@@ -168,6 +168,7 @@ if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e'
 $ModelList = docker exec d0a1-ollama ollama list 2>$null
 if ("$ModelList" -match 'qwen3:4b') {
     Info 'Modelo qwen3:4b ya descargado (volumen intacto). Omitiendo descarga.'
+    cmd /c docker exec d0a1-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf' '>' NUL '2>&1'
 } else {
     # --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
 
@@ -186,7 +187,7 @@ foreach ($Url in $HfUrls) {
 if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     Info 'Importando modelo en Ollama...'
     docker cp "$Gguf" d0a1-ollama:/root/.ollama/import.gguf
-    docker exec d0a1-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+    docker exec d0a1-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     $CreateOk = ($LASTEXITCODE -eq 0)
     docker exec d0a1-ollama rm -f /root/.ollama/import.gguf | Out-Null
     Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
@@ -199,7 +200,7 @@ if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     if ($LASTEXITCODE -eq 0) {
         $PullOk = $true
         # Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
-        docker exec d0a1-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+        docker exec d0a1-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

openwebui/docker-compose.yml

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

wordpress/deploy.ps1

@@ -205,6 +205,7 @@ if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e'
 $ModelList = docker exec d0a1-wp-ollama ollama list 2>$null
 if ("$ModelList" -match 'qwen3:4b') {
     Info 'Modelo qwen3:4b ya descargado (volumen intacto). Omitiendo descarga.'
+    cmd /c docker exec d0a1-wp-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf' '>' NUL '2>&1'
 } else {
     # --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
 
@@ -223,7 +224,7 @@ foreach ($Url in $HfUrls) {
 if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     Info 'Importando modelo en Ollama...'
     docker cp "$Gguf" d0a1-wp-ollama:/root/.ollama/import.gguf
-    docker exec d0a1-wp-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+    docker exec d0a1-wp-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     $CreateOk = ($LASTEXITCODE -eq 0)
     docker exec d0a1-wp-ollama rm -f /root/.ollama/import.gguf | Out-Null
     Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
@@ -236,7 +237,7 @@ if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 2400000000) {
     if ($LASTEXITCODE -eq 0) {
         $PullOk = $true
         # Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
-        docker exec d0a1-wp-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+        docker exec d0a1-wp-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

wordpress/docker-compose.yml

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