refactor: remove references to unsupported model claude-3-sonnet-20240229 (#32281)

Addresses some (but not all) test issues brought about in #32280

Author: mdrxy

cookbook/tool_call_messages.ipynb

@@ -34,7 +34,7 @@
     "tools = [multiply, exponentiate, add]\n",
     "\n",
     "gpt35 = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0).bind_tools(tools)\n",
-    "claude3 = ChatAnthropic(model=\"claude-3-sonnet-20240229\").bind_tools(tools)\n",
+    "claude3 = ChatAnthropic(model=\"claude-3-7-sonnet-20250219\").bind_tools(tools)\n",
     "llm_with_tools = gpt35.configurable_alternatives(\n",
     "    ConfigurableField(id=\"llm\"), default_key=\"gpt35\", claude3=claude3\n",
     ")"
@@ -113,14 +113,15 @@
     {
      "data": {
       "text/plain": [
-       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
-       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 58, 'prompt_tokens': 168, 'total_tokens': 226}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-528302fc-7acf-4c11-82c4-119ccf40c573-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8, 'y': 2.743}, 'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc'}, {'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp'}]),\n",
-       "  ToolMessage(content='300.03770462067547', tool_call_id='call_6yMU2WsS4Bqgi1WxFHxtfJRc'),\n",
-       "  ToolMessage(content='-900.8841', tool_call_id='call_GAL3dQiKFF9XEV0RrRLPTvVp'),\n",
-       "  AIMessage(content='The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.', response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 251, 'total_tokens': 295}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-d1161669-ed09-4b18-94bd-6d8530df5aa8-0')]}"
+       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\", additional_kwargs={}, response_metadata={}),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_xuNXwm2P6U2Pp2pAbC1sdIBz', 'function': {'arguments': '{\"x\": 3, \"y\": 5}', 'name': 'add'}, 'type': 'function'}, {'id': 'call_0pImUJUDlYa5zfBcxxuvWyYS', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_yaownQ9TZK0dkqD1KSFyax4H', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 75, 'prompt_tokens': 131, 'total_tokens': 206, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'id': 'chatcmpl-ByJm2qxSWU3oTTSZQv64J4XQKZhA6', 'service_tier': 'default', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run--35fad027-47f7-44d3-aa8b-99f4fc24098c-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 5}, 'id': 'call_xuNXwm2P6U2Pp2pAbC1sdIBz', 'type': 'tool_call'}, {'name': 'exponentiate', 'args': {'x': 8, 'y': 2.743}, 'id': 'call_0pImUJUDlYa5zfBcxxuvWyYS', 'type': 'tool_call'}, {'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'call_yaownQ9TZK0dkqD1KSFyax4H', 'type': 'tool_call'}], usage_metadata={'input_tokens': 131, 'output_tokens': 75, 'total_tokens': 206, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}}),\n",
+       "  ToolMessage(content='8.0', tool_call_id='call_xuNXwm2P6U2Pp2pAbC1sdIBz'),\n",
+       "  ToolMessage(content='300.03770462067547', tool_call_id='call_0pImUJUDlYa5zfBcxxuvWyYS'),\n",
+       "  ToolMessage(content='-900.8841', tool_call_id='call_yaownQ9TZK0dkqD1KSFyax4H'),\n",
+       "  AIMessage(content='The results are:\\n1. 3 plus 5 is 8.\\n2. 5 raised to the power of 2.743 is approximately 300.04.\\n3. 17.24 minus 918.1241 is approximately -900.88.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 55, 'prompt_tokens': 236, 'total_tokens': 291, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'id': 'chatcmpl-ByJm345MYnpowGS90iAZAlSs7haed', 'service_tier': 'default', 'finish_reason': 'stop', 'logprobs': None}, id='run--5fa66d47-d80e-45d0-9c32-31348c735d72-0', usage_metadata={'input_tokens': 236, 'output_tokens': 55, 'total_tokens': 291, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -146,17 +147,17 @@
     {
      "data": {
       "text/plain": [
-       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
-       "  AIMessage(content=[{'text': \"Okay, let's break this down into two parts:\", 'type': 'text'}, {'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC', 'input': {'x': 3, 'y': 5}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01AkLGH8sxMHaH15yewmjwkF', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 450, 'output_tokens': 81}}, id='run-f35bfae8-8ded-4f8a-831b-0940d6ad16b6-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 5}, 'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC'}]),\n",
-       "  ToolMessage(content='8.0', tool_call_id='toolu_01DEhqcXkXTtzJAiZ7uMBeDC'),\n",
-       "  AIMessage(content=[{'id': 'toolu_013DyMLrvnrto33peAKMGMr1', 'input': {'x': 8.0, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], response_metadata={'id': 'msg_015Fmp8aztwYcce2JDAFfce3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 545, 'output_tokens': 75}}, id='run-48aaeeeb-a1e5-48fd-a57a-6c3da2907b47-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8.0, 'y': 2.743}, 'id': 'toolu_013DyMLrvnrto33peAKMGMr1'}]),\n",
-       "  ToolMessage(content='300.03770462067547', tool_call_id='toolu_013DyMLrvnrto33peAKMGMr1'),\n",
-       "  AIMessage(content=[{'text': 'So 3 plus 5 raised to the 2.743 power is 300.04.\\n\\nFor the second part:', 'type': 'text'}, {'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_015TkhfRBENPib2RWAxkieH6', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 638, 'output_tokens': 105}}, id='run-45fb62e3-d102-4159-881d-241c5dbadeed-0', tool_calls=[{'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46'}]),\n",
-       "  ToolMessage(content='-900.8841', tool_call_id='toolu_01UTmMrGTmLpPrPCF1rShN46'),\n",
-       "  AIMessage(content='Therefore, 17.24 - 918.1241 = -900.8841', response_metadata={'id': 'msg_01LgKnRuUcSyADCpxv9tPoYD', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 759, 'output_tokens': 24}}, id='run-1008254e-ccd1-497c-8312-9550dd77bd08-0')]}"
+       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\", additional_kwargs={}, response_metadata={}),\n",
+       "  AIMessage(content=[{'text': \"I'll solve these calculations for you.\\n\\nFor the first part, I need to calculate 3 plus 5 raised to the power of 2.743.\\n\\nLet me break this down:\\n1) First, I'll calculate 5 raised to the power of 2.743\\n2) Then add 3 to the result\", 'type': 'text'}, {'id': 'toolu_01L1mXysBQtpPLQ2AZTaCGmE', 'input': {'x': 5, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_01HCbDmuzdg9ATMyKbnecbEE', 'model': 'claude-3-7-sonnet-20250219', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 563, 'output_tokens': 146, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-3-7-sonnet-20250219'}, id='run--9f6469fb-bcbb-4c1c-9eec-79f6979c38e6-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 5, 'y': 2.743}, 'id': 'toolu_01L1mXysBQtpPLQ2AZTaCGmE', 'type': 'tool_call'}], usage_metadata={'input_tokens': 563, 'output_tokens': 146, 'total_tokens': 709, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}),\n",
+       "  ToolMessage(content='82.65606421491815', tool_call_id='toolu_01L1mXysBQtpPLQ2AZTaCGmE'),\n",
+       "  AIMessage(content=[{'text': \"Now I'll add 3 to this result:\", 'type': 'text'}, {'id': 'toolu_01NARC83e9obV35mZ6jYzBiN', 'input': {'x': 3, 'y': 82.65606421491815}, 'name': 'add', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_01ELwyCtVLeGC685PUFqmdz2', 'model': 'claude-3-7-sonnet-20250219', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 727, 'output_tokens': 87, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-3-7-sonnet-20250219'}, id='run--d5af3d7c-e8b7-4cc2-997a-ad2dafd08751-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 82.65606421491815}, 'id': 'toolu_01NARC83e9obV35mZ6jYzBiN', 'type': 'tool_call'}], usage_metadata={'input_tokens': 727, 'output_tokens': 87, 'total_tokens': 814, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}),\n",
+       "  ToolMessage(content='85.65606421491815', tool_call_id='toolu_01NARC83e9obV35mZ6jYzBiN'),\n",
+       "  AIMessage(content=[{'text': \"For the second part, you asked for 17.24 - 918.1241. I don't have a subtraction function available, but I can rewrite this as adding a negative number: 17.24 + (-918.1241)\", 'type': 'text'}, {'id': 'toolu_01Q6fLcZkBWZpMPCZ55WXR3N', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_01WkmDwUxWjjaKGnTtdLGJnN', 'model': 'claude-3-7-sonnet-20250219', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 832, 'output_tokens': 130, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-3-7-sonnet-20250219'}, id='run--39a6fbda-4c81-47a6-b361-524bd4ee5823-0', tool_calls=[{'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'toolu_01Q6fLcZkBWZpMPCZ55WXR3N', 'type': 'tool_call'}], usage_metadata={'input_tokens': 832, 'output_tokens': 130, 'total_tokens': 962, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}),\n",
+       "  ToolMessage(content='-900.8841', tool_call_id='toolu_01Q6fLcZkBWZpMPCZ55WXR3N'),\n",
+       "  AIMessage(content='So, the answers are:\\n1) 3 plus 5 raised to the 2.743 = 85.65606421491815\\n2) 17.24 - 918.1241 = -900.8841', additional_kwargs={}, response_metadata={'id': 'msg_015Yoc62CvdJbANGFouiQ6AQ', 'model': 'claude-3-7-sonnet-20250219', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 978, 'output_tokens': 58, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-3-7-sonnet-20250219'}, id='run--174c0882-6180-47ea-8f63-d7b747302327-0', usage_metadata={'input_tokens': 978, 'output_tokens': 58, 'total_tokens': 1036, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}})]}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -177,7 +178,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "langchain",
    "language": "python",
    "name": "python3"
   },
@@ -191,7 +192,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.16"
   }
  },
  "nbformat": 4,

docs/docs/concepts/streaming.mdx

@@ -52,7 +52,7 @@ In addition, there is a **legacy** async [astream_log](https://python.langchain.
 
 The `stream()` method returns an iterator that yields chunks of output synchronously as they are produced. You can use a `for` loop to process each chunk in real-time. For example, when using an LLM, this allows the output to be streamed incrementally as it is generated, reducing the wait time for users.
 
-The type of chunk yielded by the `stream()` and `astream()` methods depends on the component being streamed. For example, when streaming from an [LLM](/docs/concepts/chat_models) each component will be an [AIMessageChunk](/docs/concepts/messages#aimessagechunk); however, for other components, the chunk may be different. 
+The type of chunk yielded by the `stream()` and `astream()` methods depends on the component being streamed. For example, when streaming from an [LLM](/docs/concepts/chat_models) each component will be an [AIMessageChunk](/docs/concepts/messages#aimessagechunk); however, for other components, the chunk may be different.
 
 The `stream()` method returns an iterator that yields these chunks as they are produced. For example,
 
@@ -99,7 +99,7 @@ If you compose multiple Runnables using [LangChain’s Expression Language (LCEL
 <span data-heading-keywords="astream_events,stream_events,stream events"></span>
 
 :::tip
-Use the `astream_events` API to access custom data and intermediate outputs from LLM applications built entirely with [LCEL](/docs/concepts/lcel). 
+Use the `astream_events` API to access custom data and intermediate outputs from LLM applications built entirely with [LCEL](/docs/concepts/lcel).
 
 While this API is available for use with [LangGraph](/docs/concepts/architecture#langgraph) as well, it is usually not necessary when working with LangGraph, as the `stream` and `astream` methods provide comprehensive streaming capabilities for LangGraph graphs.
 :::
@@ -119,7 +119,7 @@ from langchain_core.output_parsers import StrOutputParser
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_anthropic import ChatAnthropic
 
-model = ChatAnthropic(model="claude-3-sonnet-20240229")
+model = ChatAnthropic(model="claude-3-7-sonnet-20250219")
 
 prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
 parser = StrOutputParser()
@@ -148,7 +148,7 @@ LangChain simplifies streaming from [chat models](/docs/concepts/chat_models) by
 
 ### How It Works
 
-When you call the `invoke` (or `ainvoke`) method on a chat model, LangChain will automatically switch to streaming mode if it detects that you are trying to stream the overall application. 
+When you call the `invoke` (or `ainvoke`) method on a chat model, LangChain will automatically switch to streaming mode if it detects that you are trying to stream the overall application.
 
 Under the hood, it'll have `invoke` (or `ainvoke`) use the `stream` (or `astream`) method to generate its output. The result of the invocation will be the same as far as the code that was using `invoke` is concerned; however, while the chat model is being streamed, LangChain will take care of invoking `on_llm_new_token` events in LangChain's [callback system](/docs/concepts/callbacks). These callback events
 allow LangGraph `stream`/`astream` and `astream_events` to surface the chat model's output in real-time.
@@ -158,14 +158,14 @@ Example:
 ```python
 def node(state):
     ...
-    # The code below uses the invoke method, but LangChain will 
+    # The code below uses the invoke method, but LangChain will
     # automatically switch to streaming mode
-    # when it detects that the overall 
+    # when it detects that the overall
     # application is being streamed.
     ai_message = model.invoke(state["messages"])
     ...
 
-for chunk in compiled_graph.stream(..., mode="messages"): 
+for chunk in compiled_graph.stream(..., mode="messages"):
     ...
 ```
 ## Async Programming