From 816ef4ddc6eec81cc274587c40be7cb18357a8d5 Mon Sep 17 00:00:00 2001
From: Hyperling <me@hyperling.com>
Date: Fri, 9 Oct 2026 15:18:03 -0700
Subject: [PATCH] llm, simplify Continue config, add a function for pulling the
 LLMs outside of Ansible, adjust ollama settings.

---
 tasks/workstation/linux/software/llm.yml | 62 +++++++++++++++++-------
 1 file changed, 44 insertions(+), 18 deletions(-)

diff --git a/tasks/workstation/linux/software/llm.yml b/tasks/workstation/linux/software/llm.yml
index d7e5f66..328a548 100644
--- a/tasks/workstation/linux/software/llm.yml
+++ b/tasks/workstation/linux/software/llm.yml
@@ -33,7 +33,7 @@
         zerocode: zerocode
         qwen_code: qwen-code
         # Good to keep low to prevent swap usage.
-        llm_concurrency: "{{ ansible_memtotal_mb / 64000 | round(0, method='ceil') | int  }}"
+        llm_concurrency: "{{ ansible_memtotal_mb / 64000 | round(0, method='ceil') | int }}"
         # Allow having multiple chats open without them just waiting each other.
         llm_parallel: "{{ ansible_processor_vcpus / 8 | round(0, method='ceil') | int }}"
         # Most LLMs take a coefficient of about 1.2 to 1.5 of their file size in
@@ -186,10 +186,10 @@
               exec 2>&1
               export HOME={{ user_user.home }}
               # Timeouts #
-              export OLLAMA_LOAD_TIMEOUT=30m # default is 5m
+              export OLLAMA_LOAD_TIMEOUT=20m # default is 5m
               export OLLAMA_REQUEST_TIMEOUT=3600 # default 300 (unconfirmed, not in the list of --help vars)
               # Resource Usage #
-              export OLLAMA_KEEP_ALIVE=20m # default 5m
+              export OLLAMA_KEEP_ALIVE=20m # default is 5m
               export OLLAMA_MAX_LOADED_MODELS={{ llm_concurrency }} # default is 3 if using CPUs, or 3 * NumGPUs
               export OLLAMA_NUM_PARALLEL={{ llm_parallel }} # default is 1 and applies per-model (unconfirmed)
               export OLLAMA_CONTEXT_LENGTH={{ llm_context }} # default is 4096, https://docs.ollama.com/faq#how-can-i-specify-the-context-window-size
@@ -323,6 +323,42 @@
     #    create: false
     #    backup: true
 
+
+    - name: Workstation | Linux | Software | LLMs | Models | ollama | Manual Script
+      ansible.builtin.blockinfile:
+        path: "{{ user_user.home }}/{{ item }}"
+        marker: "# {mark} ANSIBLE MANAGED BLOCK | ollama | Manual Script"
+        content: |
+          function pull_llms() {
+            echo "Manually Pulling Models"
+            {% for llm in llm_installs %}
+
+            echo -e "\n\n Starting {{ llm.model }} \n\n"
+            ollama pull {{ llm.model }} || {
+              status=$?
+              echo "ERROR: Pull failed with status $status, exiting."
+              exit $status
+            }
+            {% endfor %}
+            echo "Done!!"
+          }
+          alias pull-llms="pull_llms "
+          alias pull-models="pull_llms "
+          alias pull-ai="pull_llms "
+        state: present
+        create: false
+        backup: true
+      loop:
+        - .bashrc
+        - .zshrc
+
+    - name: Workstation | Linux | Software | LLMs | Models | ollama | Manual Script | Message
+      ansible.builtin.debug:
+        msg: |
+          The next task may take hours, if not days. if you'd a status bar,
+          I highly recommed reloading your RC file and running `pull-models`.
+          That will give you a much better idea of what's going on.
+
     - name: Workstation | Linux | Software | LLMs | Models | ollama | Install
       ansible.builtin.shell: |
         set -o pipefail
@@ -391,24 +427,14 @@
           version: 1.0.0
           schema: v1
           models:
-        mode: "0644"
-
-    - name: Workstation | Linux | Software | LLMs | Models | Continue | Models
-      ansible.builtin.blockinfile:
-        path: "{{ user_user.home }}/.continue/config.yml"
-        marker: "# {mark} ANSIBLE MANAGED BLOCK | llm.yml | Continue"
-        insertafter: EOF
-        block: |
-          {% for llm in llm_installs %}
-            - name: llm.provider
+            {% for llm in llm_installs %}
+            - name: {{ llm.provider }}
               provider: ollama
-              model: llm.model
+              model: {{ llm.model }}
               defaultCompletionOptions:
                 contextLength: {{ llm_context }}
                 maxTokens: {{ llm_context }}
-          {% endfor %}
-        state: present
-        create: false
-        backup: true
+            {% endfor %}
+        mode: "0644"
 
   when: ansible_pkg_mgr == "pacman"