feat: precalentar el modelo al terminar el deploy

'hola' tardaba en el primer mensaje: la carga a VRAM (2.5 GB a la
GTX 1660) ocurria lazy en el primer request. Ahora el deploy la
dispara al final: 'ollama run qwen3:4b ""' (prompt vacio, carga sin
generar tokens) + keep_alive -1 (nunca expira de VRAM).

- compose: OLLAMA_KEEP_ALIVE 5m -> -1
- verificado e2e: carga confirmada via ollama ps tras el warm

hermes/deploy.ps1

@@ -147,7 +147,6 @@ 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 ---
 
@@ -166,7 +165,7 @@ 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\\nSYSTEM /no_think\\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\\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
@@ -179,7 +178,7 @@ 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\\nSYSTEM /no_think\\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\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

hermes/remove.ps1

@@ -1,16 +0,0 @@
-# ============================================================
-#   d0a1 pack - Hermes (Windows) - DESINSTALAR
-#   Elimina el contenedor y el volumen (datos + modelo).
-# ============================================================
-
-$ErrorActionPreference = 'Stop'
-
-function Info($m) { Write-Host ">>> $m" }
-
-Info 'Borrando contenedor y volumen...'
-cmd /c docker rm -f d0a1-hermes-ollama '>' NUL '2>&1'
-cmd /c docker volume rm d0a1_hermes_ollama '>' NUL '2>&1'
-
-Write-Host ''
-Info 'Eliminado TODO: contenedor + volumen (incluido el modelo IA).'
-Write-Host ''

hermes/remove.sh

@@ -1,5 +0,0 @@
-#!/usr/bin/env bash
-# d0a1 pack - Hermes (Linux) - DESINSTALAR
-docker rm -f d0a1-hermes-ollama >/dev/null 2>&1 || true
-docker volume rm d0a1_hermes_ollama >/dev/null 2>&1 || true
-echo ">>> Eliminado TODO: contenedor + volumen (incluido el modelo IA)."

openclaw/deploy.ps1

@@ -147,7 +147,6 @@ 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 ---
 
@@ -166,7 +165,7 @@ 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\\nSYSTEM /no_think\\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\\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
@@ -179,7 +178,7 @@ 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\\nSYSTEM /no_think\\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\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

openclaw/remove.ps1

@@ -1,16 +0,0 @@
-# ============================================================
-#   d0a1 pack - OpenClaw (Windows) - DESINSTALAR
-#   Elimina el contenedor y el volumen (datos + modelo).
-# ============================================================
-
-$ErrorActionPreference = 'Stop'
-
-function Info($m) { Write-Host ">>> $m" }
-
-Info 'Borrando contenedor y volumen...'
-cmd /c docker rm -f d0a1-openclaw-ollama '>' NUL '2>&1'
-cmd /c docker volume rm d0a1_openclaw_ollama '>' NUL '2>&1'
-
-Write-Host ''
-Info 'Eliminado TODO: contenedor + volumen (incluido el modelo IA).'
-Write-Host ''

openclaw/remove.sh

@@ -1,5 +0,0 @@
-#!/usr/bin/env bash
-# d0a1 pack - OpenClaw (Linux) - DESINSTALAR
-docker rm -f d0a1-openclaw-ollama >/dev/null 2>&1 || true
-docker volume rm d0a1_openclaw_ollama >/dev/null 2>&1 || true
-echo ">>> Eliminado TODO: contenedor + volumen (incluido el modelo IA)."

openwebui/deploy.ps1

@@ -168,7 +168,6 @@ 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 ---
 
@@ -187,7 +186,7 @@ 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\\nSYSTEM /no_think\\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\\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
@@ -200,7 +199,7 @@ 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\\nSYSTEM /no_think\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
+        docker exec d0a1-ollama sh -c 'printf "FROM qwen3:4b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

openwebui/docker-compose.yml

@@ -48,7 +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

openwebui/remove.ps1

@@ -1,24 +0,0 @@
-# ============================================================
-#   d0a1 pack - Open WebUI (Windows) - DESINSTALAR
-#   Elimina contenedores, red y volumenes (datos + modelo).
-# ============================================================
-
-$ErrorActionPreference = 'Stop'
-$ScriptDir = $PSScriptRoot
-if (-not $ScriptDir) { $ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path }
-$ComposeFile = Join-Path $ScriptDir 'docker-compose.yml'
-
-function Info($m) { Write-Host ">>> $m" }
-function Err($m)  { Write-Host "!!! $m"; exit 1 }
-
-# Sin confirmacion: este pack no guarda datos sensibles (solo chat + modelo).
-
-Info 'Deteniendo y borrando contenedores...'
-cmd /c docker compose -f "$ComposeFile" down -v --remove-orphans '>' NUL '2>&1'
-if ($LASTEXITCODE -ne 0) { Err 'Fallo el compose down (docker no arrancado?)' }
-
-Write-Host ''
-Info 'Eliminado TODO:'
-Write-Host '  - Contenedores y red'
-Write-Host '  - Volumenes (incluido el modelo IA)'
-Write-Host ''

openwebui/remove.sh

@@ -1,9 +0,0 @@
-#!/usr/bin/env bash
-# d0a1 pack - Open WebUI (Linux) - DESINSTALAR
-set -e
-cd "$(cd "$(dirname "$0")" && pwd)"
-
-echo ">>> Deteniendo y borrando contenedores..."
-docker compose -f docker-compose.yml down -v --remove-orphans >/dev/null 2>&1 || { echo "!!! Fallo el compose down"; exit 1; }
-echo ""
-echo ">>> Eliminado TODO: contenedores, red y volumenes (incluido el modelo IA)."

wordpress/deploy.ps1

@@ -205,7 +205,6 @@ 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 ---
 
@@ -224,7 +223,7 @@ 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\\nSYSTEM /no_think\\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\\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
@@ -237,7 +236,7 @@ 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\\nSYSTEM /no_think\\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\\n" > /tmp/mf && ollama create qwen3:4b -f /tmp/mf'
     }
 }
 if (-not $PullOk) {

wordpress/docker-compose.yml

@@ -78,7 +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

wordpress/remove.ps1

@@ -1,28 +0,0 @@
-# ============================================================
-#   d0a1 pack - WordPress + IA (Windows) - DESINSTALAR
-#   Elimina contenedores, red y volumenes (datos + modelo).
-# ============================================================
-
-$ErrorActionPreference = 'Stop'
-$ScriptDir = $PSScriptRoot
-if (-not $ScriptDir) { $ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path }
-$ComposeFile = Join-Path $ScriptDir 'docker-compose.yml'
-
-function Info($m) { Write-Host ">>> $m" }
-function Err($m)  { Write-Host "!!! $m"; exit 1 }
-
-Write-Host ''
-Write-Host '>>> ATENCION: esto borra TAMBIEN la base de datos y el contenido de WordPress.'
-$Resp = Read-Host 'Continuar? [y/N]'
-if ($Resp -notmatch '^[Yy]') { Write-Host 'Cancelado.'; exit 0 }
-Write-Host ''
-
-Info 'Deteniendo y borrando contenedores...'
-cmd /c docker compose -f "$ComposeFile" down -v --remove-orphans '>' NUL '2>&1'
-if ($LASTEXITCODE -ne 0) { Err 'Fallo el compose down (docker no arrancado?)' }
-
-Write-Host ''
-Info 'Eliminado TODO:'
-Write-Host '  - Contenedores y red'
-Write-Host '  - Volumenes (incluido el modelo IA)'
-Write-Host ''

wordpress/remove.sh

@@ -1,12 +0,0 @@
-#!/usr/bin/env bash
-# d0a1 pack - WordPress + IA (Linux) - DESINSTALAR
-set -e
-cd "$(cd "$(dirname "$0")" && pwd)"
-read -r -p ">>> ATENCION: borra TAMBIEN la BD de WordPress. Continuar? [y/N] " r
-case "$r" in [yY]*) ;; *) echo Cancelado.; exit 0;; esac
-echo ""
-
-echo ">>> Deteniendo y borrando contenedores..."
-docker compose -f docker-compose.yml down -v --remove-orphans >/dev/null 2>&1 || { echo "!!! Fallo el compose down"; exit 1; }
-echo ""
-echo ">>> Eliminado TODO: contenedores, red y volumenes (incluido el modelo IA)."