Bump Ollama model to qwen2.5:1.5b for better instruction following

The 0.5b model was too small to reliably follow simple prompts like
'Say Hello World', causing test assertion failures. The 1.5b model
follows instructions more reliably while still being small enough
for fast CI pulls (~1GB).

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

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

@@ -157,7 +157,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_CHAT_MODEL: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
       LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
-      OLLAMA_MODEL: qwen2.5:0.5b
+      OLLAMA_MODEL: qwen2.5:1.5b
       OLLAMA_EMBEDDING_MODEL: nomic-embed-text
     defaults:
       run:
@@ -180,7 +180,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.ollama/models
-          key: ollama-models-qwen2.5-0.5b-nomic-embed-text-v1
+          key: ollama-models-qwen2.5-1.5b-nomic-embed-text-v1
       - name: Start Ollama and pull models
         run: |
           ollama serve &
@@ -190,7 +190,7 @@ jobs:
             fi
             sleep 1
           done
-          ollama pull qwen2.5:0.5b
+          ollama pull qwen2.5:1.5b
           ollama pull nomic-embed-text
         working-directory: .
       - name: Start local MCP server