Add retry logic and port-conflict fix for Ollama CI setup

- Kill any auto-started Ollama before launching serve (fixes port
  conflict: 'address already in use')
- Retry ollama pull up to 3 times with 15s backoff (fixes 429 rate
  limit failures)
- Applied to both python-merge-tests.yml and python-integration-tests.yml

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.github/workflows/python-integration-tests.yml

@@ -183,6 +183,9 @@ jobs:
           key: ollama-models-qwen2.5-1.5b-nomic-embed-text-v1
       - name: Start Ollama and pull models
         run: |
+          # Stop any Ollama instance auto-started by the install script
+          pkill ollama || true
+          sleep 2
           ollama serve &
           for i in $(seq 1 30); do
             if curl -sf http://localhost:11434/api/tags > /dev/null 2>&1; then
@@ -190,8 +193,16 @@ jobs:
             fi
             sleep 1
           done
-          ollama pull qwen2.5:1.5b
-          ollama pull nomic-embed-text
+          # Pull models with retry for transient 429 rate limits
+          for model in qwen2.5:1.5b nomic-embed-text; do
+            for attempt in 1 2 3; do
+              if ollama pull "$model"; then
+                break
+              fi
+              echo "Retry $attempt for $model (waiting 15s)..."
+              sleep 15
+            done
+          done
         working-directory: .
       - name: Start local MCP server
         id: local-mcp