llm, enhance comments in the ollama run script.

tasks/workstation/linux/software/llm.yml

@@ -182,20 +182,25 @@
             dest: "{{ ollama_runit_script }}"
             content: |
               #!/bin/sh -e
-              # Allow pulling LLMs for use with ZeroClaw.
+              # Allow pulling and accessing LLMs via tools.
               exec 2>&1
+              ### Required ###
               export HOME={{ user_user.home }}
-              # Timeouts #
+              ### Timeouts ###
               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 #
+              ### Resource Usage ###
               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
               export OLLAMA_MAX_QUEUE=999 # default is 512 (unconfirmed)
-              # Prevent Data Loss #
-              export OLLAMA_NOPRUNE=1 # Default is 0, which causes unfinished pulls to be deleeted after 1 hour. (unconfirmed)
+              ### Prevent Data Loss ###
+              # OLLAMA_NOPRUNE
+              #   Default is 0, which causes unfinished pulls to be deleted
+              #   after 1 hour of inactivity. To manually clean partials, run:
+              #     `rm ~/.ollama/models/blobs/*-partial*`
+              export OLLAMA_NOPRUNE=1
               exec chpst -u {{ user }} ollama serve
             mode: "0755"