docker-compose.yml

@@ -163,9 +163,11 @@ services:
       - no-new-privileges:true
     # The image ENTRYPOINT is `ollama`, so override it to a shell; the image has
     # no curl, so readiness is probed with `ollama list` instead of a curl loop.
+    # The pull is guarded by a `grep` on the cached model list so an already-cached
+    # model exits clean without a registry round-trip (offline-safe re-up).
     entrypoint: ["/bin/sh", "-c"]
     command:
-      - "ollama serve & until ollama list >/dev/null 2>&1; do sleep 1; done && ollama pull qwen2.5:7b-instruct-q4_K_M"
+      - "ollama serve & until ollama list >/dev/null 2>&1; do sleep 1; done && (ollama list | grep -q 'qwen2.5:7b-instruct-q4_K_M' || ollama pull qwen2.5:7b-instruct-q4_K_M)"
 
   # --- Ollama: LLM inference server ---
   # Serves the pre-pulled model for NL search inference.