feat: make multi-turn tool call tests work with llama4 (#1886)

Running full Tool Calling required some updates to work e2e.
- Remove `python_start` and `python_end` tags 
- Tool Call messages and Tool Resposne messages should end with
`<|eom|>`
- System prompt needed updates 
```
You are a helpful assisant who can can answer general questions or invoke tools when necessary.
In addition to tool calls, you should also augment your responses by using the tool outputs.
```

### Test Plan 
- Start server with meta-reference 
```
LLAMA_STACK_DISABLE_VERSION_CHECK=1 LLAMA_MODELS_DEBUG=1 INFERENCE_MODEL=meta-llama/$MODEL  llama stack run meta-reference-gpu 
``` 
- Added **NEW** tests with 5 test cases for multi-turn tool calls 
```
pytest -s -v --stack-config http://localhost:8321 tests/integration/inference/test_text_inference.py --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct
``` 
- Also verified all vision and agent tests pass

llama_stack/models/llama/llama3/prompt_templates/system_prompts.py

@@ -279,6 +279,10 @@ class PythonListCustomToolGenerator(PromptTemplateGeneratorBase):  # noqa: N801
                 {% endif -%}
                 {%- endfor %}
             ]
+
+            You can answer general questions or invoke tools when necessary.
+            In addition to tool calls, you should also augment your responses by using the tool outputs.
+
             """
         )
         return PromptTemplate(

llama_stack/models/llama/llama4/chat_format.py

@@ -216,9 +216,12 @@ class ChatFormat:
                 content = ToolUtils.encode_tool_call(t, tool_prompt_format)
                 _process_content(content)
 
+        # Tool calls and Tool Response messages should be eom
         eom = False
         if message.role == "assistant":
-            eom = message.stop_reason == StopReason.end_of_message
+            eom = message.stop_reason == StopReason.end_of_message or message.tool_calls
+        elif message.role == "tool":
+            eom = True
 
         tokens.append(self.tokenizer.special_tokens["<|eom|>" if eom else "<|eot|>"])
         return tokens, images