ollama: thinking, tool streaming, docs, tests (#31772)

* New `reasoning` (bool) param to support toggling [Ollama
thinking](https://ollama.com/blog/thinking) (#31573, #31700). If
`reasoning=True`, Ollama's `thinking` content will be placed in the
model responses' `additional_kwargs.reasoning_content`.
  * Supported by:
    * ChatOllama (class level, invocation level TODO)
    * OllamaLLM (TODO)
* Added tests to ensure streaming tool calls is successful (#29129)
* Refactored tests that relied on `extract_reasoning()`
* Myriad docs additions and consistency/typo fixes
* Improved type safety in some spots

Closes #29129
Addresses #31573 and #31700
Supersedes #31701

Author: mdrxy

docs/docs/how_to/callbacks_custom_events.ipynb

@@ -38,11 +38,11 @@
     "\n",
     "\n",
     ":::caution COMPATIBILITY\n",
-    "LangChain cannot automatically propagate configuration, including callbacks necessary for astream_events(), to child runnables if you are running async code in python<=3.10. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
+    "LangChain cannot automatically propagate configuration, including callbacks necessary for astream_events(), to child runnables if you are running async code in `python<=3.10`. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
     "\n",
-    "If you are running python&lt;=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
+    "If you are running `python<=3.10`, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
     "\n",
-    "If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in other Python versions.\n",
+    "If you are running `python>=3.11`, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in other Python versions.\n",
     ":::"
    ]
   },

docs/docs/how_to/tool_stream_events.ipynb

@@ -16,15 +16,15 @@
     "\n",
     ":::\n",
     "\n",
-    "If you have [tools](/docs/concepts/tools/) that call [chat models](/docs/concepts/chat_models/), [retrievers](/docs/concepts/retrievers/), or other [runnables](/docs/concepts/runnables/), you may want to access internal events from those runnables or configure them with additional properties. This guide shows you how to manually pass parameters properly so that you can do this using the `astream_events()` method.\n",
+    "If you have [tools](/docs/concepts/tools/) that call [chat models](/docs/concepts/chat_models/), [retrievers](/docs/concepts/retrievers/), or other [runnables](/docs/concepts/runnables/), you may want to access [internal events](https://python.langchain.com/docs/how_to/streaming/#event-reference) from those runnables or configure them with additional properties. This guide shows you how to manually pass parameters properly so that you can do this using the `astream_events()` method.\n",
     "\n",
     ":::caution Compatibility\n",
     "\n",
-    "LangChain cannot automatically propagate configuration, including callbacks necessary for `astream_events()`, to child runnables if you are running `async` code in `python<=3.10`. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
+    "LangChain cannot automatically propagate configuration, including callbacks necessary for `astream_events()`, to child runnables if you are running `async` code in `python<=3.10`. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
     "\n",
-    "If you are running python&lt;=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
+    "If you are running `python<=3.10`, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
     "\n",
-    "If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in older Python versions.\n",
+    "If you are running `python>=3.11`, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in older Python versions.\n",
     "\n",
     "This guide also requires `langchain-core>=0.2.16`.\n",
     ":::\n",

docs/docs/how_to/tool_streaming.ipynb

@@ -224,6 +224,13 @@
    "source": [
     "print(type(gathered.tool_calls[0][\"args\"]))"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note the key difference: accumulating `tool_call_chunks` captures the raw tool arguments as an unparsed string as they are streamed. In contrast, **accumulating** `tool_calls` demonstrates partial parsing by progressively converting the streamed argument string into a valid, usable dictionary at each step of the process."
+   ]
   }
  ],
  "metadata": {

libs/core/langchain_core/language_models/llms.py

@@ -1414,9 +1414,10 @@ def save(self, file_path: Union[Path, str]) -> None:
             ValueError: If the file path is not a string or Path object.
 
         Example:
-        .. code-block:: python
 
-            llm.save(file_path="path/llm.yaml")
+            .. code-block:: python
+
+                llm.save(file_path="path/llm.yaml")
         """
         # Convert file to Path object.
         save_path = Path(file_path)

libs/core/langchain_core/runnables/base.py

@@ -1160,30 +1160,29 @@ async def astream_events(
 
         A StreamEvent is a dictionary with the following schema:
 
-        - ``event``: **str** - Event names are of the
-            format: on_[runnable_type]_(start|stream|end).
+        - ``event``: **str** - Event names are of the format:
+          on_[runnable_type]_(start|stream|end).
         - ``name``: **str** - The name of the Runnable that generated the event.
-        - ``run_id``: **str** - randomly generated ID associated with the given execution of
-            the Runnable that emitted the event.
-            A child Runnable that gets invoked as part of the execution of a
-            parent Runnable is assigned its own unique ID.
-        - ``parent_ids``: **list[str]** - The IDs of the parent runnables that
-            generated the event. The root Runnable will have an empty list.
-            The order of the parent IDs is from the root to the immediate parent.
-            Only available for v2 version of the API. The v1 version of the API
-            will return an empty list.
+        - ``run_id``: **str** - randomly generated ID associated with the given
+          execution of the Runnable that emitted the event. A child Runnable that gets
+          invoked as part of the execution of a parent Runnable is assigned its own
+          unique ID.
+        - ``parent_ids``: **list[str]** - The IDs of the parent runnables that generated
+          the event. The root Runnable will have an empty list. The order of the parent
+          IDs is from the root to the immediate parent. Only available for v2 version of
+          the API. The v1 version of the API will return an empty list.
         - ``tags``: **Optional[list[str]]** - The tags of the Runnable that generated
-            the event.
-        - ``metadata``: **Optional[dict[str, Any]]** - The metadata of the Runnable
-            that generated the event.
+          the event.
+        - ``metadata``: **Optional[dict[str, Any]]** - The metadata of the Runnable that
+          generated the event.
         - ``data``: **dict[str, Any]**
 
 
         Below is a table that illustrates some events that might be emitted by various
         chains. Metadata fields have been omitted from the table for brevity.
         Chain definitions have been included after the table.
 
-        **ATTENTION** This reference table is for the V2 version of the schema.
+        .. NOTE:: This reference table is for the V2 version of the schema.
 
         +----------------------+------------------+---------------------------------+-----------------------------------------------+-------------------------------------------------+
         | event                | name             | chunk                           | input                                         | output                                          |