fix streaming, remove exit_conditions example

Author: julian-risch

tutorials/43_Building_a_Tool_Calling_Agent.ipynb

@@ -122,7 +122,7 @@
     "\n",
     "# Run the agent with a query\n",
     "result = agent.run(\n",
-    "    messages=[ChatMessage.from_user(\"Find information about Haystack\")]\n",
+    "    messages=[ChatMessage.from_user(\"Find information about Haystack AI framework\")]\n",
     ")\n",
     "\n",
     "# Print the final response\n",
@@ -137,13 +137,13 @@
     "The Agent has a couple of optional parameters that let you customize it's behavior:\n",
     "- `system_prompt` for defining a system prompt with instructions for the Agent's LLM\n",
     "- `exit_conditions` that will cause the agent to return. It's a list of strings and the items can be `\"text\"`, which means that the Agent will exit as soon as the LLM replies only with a text response,\n",
-    "or specific tool names.\n",
+    "or specific tool names, which make the Agent return right after a tool with that name was called.\n",
     "- `state_schema` for the State that is shared across one agent invocation run. It defines extra information – such as documents or context – that tools can read from or write to during execution. You can use this schema to pass parameters that tools can both produce and consume.\n",
     "- `streaming_callback` to stream the tokens from the LLM directly to output.\n",
     "- `raise_on_tool_invocation_failure` to decide if the agent should raise an exception when a tool invocation fails. If set to False, the exception will be turned into a chat message and passed to the LLM. It can then try to improve with the next tool invocation.\n",
     "- `max_agent_steps` to limit how many times the Agent can call tools and prevent endless loops.\n",
     "\n",
-    "In the previous example, the Agent was allowed to call the tool multiple times until the default exit condition was met: a text response. Now, let's return right after calling `web_tool` or after the LLM generated text, whatever happens first. Let's also use streaming so that we see the tokens of the response while they are being generated."
+    "When `exit_conditions` is set to the default [\"text\"], you can enable streaming so that we see the tokens of the response while they are being generated."
    ]
   },
   {
@@ -152,11 +152,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from haystack.components.generators.utils import print_streaming_chunk\n",
+    "\n",
     "agent = Agent(\n",
     "    chat_generator=OpenAIChatGenerator(),\n",
     "    tools=[web_tool],\n",
-    "    exit_conditions=[\"text\", \"web_tool\"],\n",
-    "    streaming_callback=lambda chunk: print(chunk.content, end=\"\", flush=True),\n",
+    "    streaming_callback=print_streaming_chunk,\n",
     ")\n",
     "\n",
     "result = agent.run(\n",