diff --git a/libs/core/langchain_core/language_models/chat_models.py b/libs/core/langchain_core/language_models/chat_models.py
index c01b11b28d0..291bd833f2d 100644
--- a/libs/core/langchain_core/language_models/chat_models.py
+++ b/libs/core/langchain_core/language_models/chat_models.py
@@ -1517,7 +1517,7 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
@@ -1530,16 +1530,17 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
         Returns:
             A Runnable that takes same inputs as a `langchain_core.language_models.chat.BaseChatModel`.
 
-            If `include_raw` is False and `schema` is a Pydantic class, Runnable outputs
-            an instance of `schema` (i.e., a Pydantic object).
+                If `include_raw` is False and `schema` is a Pydantic class, Runnable outputs
+                an instance of `schema` (i.e., a Pydantic object).
 
-            Otherwise, if `include_raw` is False then Runnable outputs a dict.
+                Otherwise, if `include_raw` is False then Runnable outputs a dict.
 
-            If `include_raw` is True, then Runnable outputs a dict with keys:
+                If `include_raw` is True, then Runnable outputs a dict with keys:
 
-            - `'raw'`: BaseMessage
-            - `'parsed'`: None if there was a parsing error, otherwise the type depends on the `schema` as described above.
-            - `'parsing_error'`: BaseException | None
+                - `'raw'`: BaseMessage
+                - `'parsed'`: None if there was a parsing error, otherwise the type
+                    depends on the `schema` as described above.
+                - `'parsing_error'`: BaseException | None
 
         Example: Pydantic schema (include_raw=False):
             ```python
@@ -1620,7 +1621,7 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
             ```
 
         !!! warning "Behavior changed in 0.2.26"
-                Added support for TypedDict class.
+            Added support for TypedDict class.
 
         """  # noqa: E501
         _ = kwargs.pop("method", None)
diff --git a/libs/core/langchain_core/runnables/base.py b/libs/core/langchain_core/runnables/base.py
index 93c7413e068..d56f663c80d 100644
--- a/libs/core/langchain_core/runnables/base.py
+++ b/libs/core/langchain_core/runnables/base.py
@@ -860,7 +860,7 @@ class Runnable(ABC, Generic[Input, Output]):
 
         The default implementation of batch works well for IO bound runnables.
 
-        Subclasses should override this method if they can batch more efficiently;
+        Subclasses must override this method if they can batch more efficiently;
         e.g., if the underlying `Runnable` uses an API which supports a batch mode.
 
         Args:
@@ -992,7 +992,7 @@ class Runnable(ABC, Generic[Input, Output]):
 
         The default implementation of `batch` works well for IO bound runnables.
 
-        Subclasses should override this method if they can batch more efficiently;
+        Subclasses must override this method if they can batch more efficiently;
         e.g., if the underlying `Runnable` uses an API which supports a batch mode.
 
         Args:
@@ -1112,7 +1112,7 @@ class Runnable(ABC, Generic[Input, Output]):
     ) -> Iterator[Output]:
         """Default implementation of `stream`, which calls `invoke`.
 
-        Subclasses should override this method if they support streaming output.
+        Subclasses must override this method if they support streaming output.
 
         Args:
             input: The input to the `Runnable`.
@@ -1133,7 +1133,7 @@ class Runnable(ABC, Generic[Input, Output]):
     ) -> AsyncIterator[Output]:
         """Default implementation of `astream`, which calls `ainvoke`.
 
-        Subclasses should override this method if they support streaming output.
+        Subclasses must override this method if they support streaming output.
 
         Args:
             input: The input to the `Runnable`.
@@ -1497,7 +1497,7 @@ class Runnable(ABC, Generic[Input, Output]):
 
         Default implementation of transform, which buffers input and calls `astream`.
 
-        Subclasses should override this method if they can start producing output while
+        Subclasses must override this method if they can start producing output while
         input is still being generated.
 
         Args:
@@ -1542,7 +1542,7 @@ class Runnable(ABC, Generic[Input, Output]):
 
         Default implementation of atransform, which buffers input and calls `astream`.
 
-        Subclasses should override this method if they can start producing output while
+        Subclasses must override this method if they can start producing output while
         input is still being generated.
 
         Args:
diff --git a/libs/core/langchain_core/runnables/config.py b/libs/core/langchain_core/runnables/config.py
index a77718414c1..d2094137640 100644
--- a/libs/core/langchain_core/runnables/config.py
+++ b/libs/core/langchain_core/runnables/config.py
@@ -75,26 +75,26 @@ class RunnableConfig(TypedDict, total=False):
     max_concurrency: int | None
     """
     Maximum number of parallel calls to make. If not provided, defaults to
-    ThreadPoolExecutor's default.
+    `ThreadPoolExecutor`'s default.
     """
 
     recursion_limit: int
     """
-    Maximum number of times a call can recurse. If not provided, defaults to 25.
+    Maximum number of times a call can recurse. If not provided, defaults to `25`.
     """
 
     configurable: dict[str, Any]
     """
-    Runtime values for attributes previously made configurable on this Runnable,
-    or sub-Runnables, through .configurable_fields() or .configurable_alternatives().
-    Check .output_schema() for a description of the attributes that have been made
+    Runtime values for attributes previously made configurable on this `Runnable`,
+    or sub-Runnables, through `configurable_fields` or `configurable_alternatives`.
+    Check `output_schema` for a description of the attributes that have been made
     configurable.
     """
 
     run_id: uuid.UUID | None
     """
     Unique identifier for the tracer run for this call. If not provided, a new UUID
-        will be generated.
+    will be generated.
     """
 
 
diff --git a/libs/partners/anthropic/langchain_anthropic/chat_models.py b/libs/partners/anthropic/langchain_anthropic/chat_models.py
index 75be16b2159..a57c2499e1e 100644
--- a/libs/partners/anthropic/langchain_anthropic/chat_models.py
+++ b/libs/partners/anthropic/langchain_anthropic/chat_models.py
@@ -2197,7 +2197,7 @@ class ChatAnthropic(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `raw`, `parsed`, and `parsing_error`.
@@ -2293,10 +2293,6 @@ class ChatAnthropic(BaseChatModel):
             #     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
             # }
             ```
-
-        !!! warning "Behavior changed in 0.1.22"
-                Added support for TypedDict class as `schema`.
-
         """  # noqa: E501
         formatted_tool = convert_to_anthropic_tool(schema)
         tool_name = formatted_tool["name"]
diff --git a/libs/partners/deepseek/langchain_deepseek/chat_models.py b/libs/partners/deepseek/langchain_deepseek/chat_models.py
index bc185d366fc..ea692a1ce54 100644
--- a/libs/partners/deepseek/langchain_deepseek/chat_models.py
+++ b/libs/partners/deepseek/langchain_deepseek/chat_models.py
@@ -395,13 +395,10 @@ class ChatDeepSeek(BaseChatOpenAI):
                 - `'json_mode'`:
                     Uses DeepSeek's [JSON mode feature](https://api-docs.deepseek.com/guides/json_mode).
 
-                !!! warning "Behavior changed in 0.1.3"
-                    Added support for `'json_mode'`.
-
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/fireworks/langchain_fireworks/chat_models.py b/libs/partners/fireworks/langchain_fireworks/chat_models.py
index 0af3bc4feb5..df4c3420732 100644
--- a/libs/partners/fireworks/langchain_fireworks/chat_models.py
+++ b/libs/partners/fireworks/langchain_fireworks/chat_models.py
@@ -693,9 +693,6 @@ class ChatFireworks(BaseChatModel):
                 for more on how to properly specify types and descriptions of
                 schema fields when specifying a Pydantic or `TypedDict` class.
 
-                !!! warning "Behavior changed in 0.1.7"
-                    Added support for TypedDict class.
-
             method: The method for steering model generation, one of:
 
                 - `'function_calling'`:
@@ -711,7 +708,7 @@ class ChatFireworks(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/groq/langchain_groq/chat_models.py b/libs/partners/groq/langchain_groq/chat_models.py
index 29ba2184ef0..30889468f51 100644
--- a/libs/partners/groq/langchain_groq/chat_models.py
+++ b/libs/partners/groq/langchain_groq/chat_models.py
@@ -838,9 +838,6 @@ class ChatGroq(BaseChatModel):
                 for more on how to properly specify types and descriptions of
                 schema fields when specifying a Pydantic or `TypedDict` class.
 
-                !!! warning "Behavior changed in 0.1.9"
-                    Added support for TypedDict class.
-
                 !!! warning "Behavior changed in 0.3.8"
                     Added support for Groq's dedicated structured output feature via
                     `method="json_schema"`.
@@ -880,7 +877,7 @@ class ChatGroq(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py b/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
index fe9f2111855..967c2a6a61a 100644
--- a/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
+++ b/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
@@ -896,7 +896,7 @@ class ChatHuggingFace(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/mistralai/langchain_mistralai/chat_models.py b/libs/partners/mistralai/langchain_mistralai/chat_models.py
index f31f96c2427..9c56f300a09 100644
--- a/libs/partners/mistralai/langchain_mistralai/chat_models.py
+++ b/libs/partners/mistralai/langchain_mistralai/chat_models.py
@@ -817,9 +817,6 @@ class ChatMistralAI(BaseChatModel):
                 for more on how to properly specify types and descriptions of
                 schema fields when specifying a Pydantic or `TypedDict` class.
 
-                !!! warning "Behavior changed in 0.1.12"
-                    Added support for TypedDict class.
-
             method: The method for steering model generation, one of:
 
                 - `'function_calling'`:
@@ -841,7 +838,7 @@ class ChatMistralAI(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/openai/langchain_openai/chat_models/azure.py b/libs/partners/openai/langchain_openai/chat_models/azure.py
index 60d663a06b3..98e99ab09f7 100644
--- a/libs/partners/openai/langchain_openai/chat_models/azure.py
+++ b/libs/partners/openai/langchain_openai/chat_models/azure.py
@@ -865,7 +865,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
@@ -945,13 +945,6 @@ class AzureChatOpenAI(BaseChatOpenAI):
             - `'parsed'`: None if there was a parsing error, otherwise the type depends on the `schema` as described above.
             - `'parsing_error'`: BaseException | None
 
-        !!! warning "Behavior changed in 0.1.20"
-            Added support for TypedDict class `schema`.
-
-        !!! warning "Behavior changed in 0.1.21"
-            Support for `strict` argument added.
-            Support for `method="json_schema"` added.
-
         !!! warning "Behavior changed in 0.3.0"
             `method` default changed from "function_calling" to "json_schema".
 
diff --git a/libs/partners/openai/langchain_openai/chat_models/base.py b/libs/partners/openai/langchain_openai/chat_models/base.py
index 9e225788403..9be2f7c1a2c 100644
--- a/libs/partners/openai/langchain_openai/chat_models/base.py
+++ b/libs/partners/openai/langchain_openai/chat_models/base.py
@@ -1676,9 +1676,6 @@ class BaseChatOpenAI(BaseChatModel):
             parallel_tool_calls: Set to `False` to disable parallel tool use.
                 Defaults to `None` (no specification, which allows parallel tool use).
             kwargs: Any additional parameters are passed directly to `bind`.
-
-        !!! warning "Behavior changed in 0.1.21"
-            Support for `strict` argument added.
         """  # noqa: E501
         if parallel_tool_calls is not None:
             kwargs["parallel_tool_calls"] = parallel_tool_calls
@@ -1766,7 +1763,7 @@ class BaseChatOpenAI(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/perplexity/langchain_perplexity/chat_models.py b/libs/partners/perplexity/langchain_perplexity/chat_models.py
index c5e25f3eeed..78ae52ce34e 100644
--- a/libs/partners/perplexity/langchain_perplexity/chat_models.py
+++ b/libs/partners/perplexity/langchain_perplexity/chat_models.py
@@ -425,7 +425,7 @@ class ChatPerplexity(BaseChatModel):
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.
diff --git a/libs/partners/xai/langchain_xai/chat_models.py b/libs/partners/xai/langchain_xai/chat_models.py
index a3e0bdbaddb..c3e1b9bdad6 100644
--- a/libs/partners/xai/langchain_xai/chat_models.py
+++ b/libs/partners/xai/langchain_xai/chat_models.py
@@ -611,7 +611,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
             include_raw:
                 If `False` then only the parsed structured output is returned. If
                 an error occurs during model output parsing it will be raised. If `True`
-                then both the raw model response (a BaseMessage) and the parsed model
+                then both the raw model response (a `BaseMessage`) and the parsed model
                 response will be returned. If an error occurs during output parsing it
                 will be caught and returned as well. The final output is always a dict
                 with keys `'raw'`, `'parsed'`, and `'parsing_error'`.