Merge remote-tracking branch 'upstream/main' into feat/add-manage-user-context-docs

Author: jjhpka

reference/python/docs/langchain/agents.md

@@ -2,6 +2,7 @@
 <!-- (`group_by_category orders `AgentState` (a class) before functions) -->
 ::: langchain.agents
     options:
+      summary: false
       group_by_category: false
       parameter_headings: true
       members:

reference/python/docs/langchain/embeddings.md

@@ -2,6 +2,7 @@
 <!-- (`group_by_category orders `Embeddings` (a class) before functions) -->
 ::: langchain.embeddings
     options:
+      summary: false
       group_by_category: false
       members:
         - init_embeddings

reference/python/docs/langchain/models.md

@@ -3,5 +3,6 @@
 ::: langchain.chat_models
     options:
       parameter_headings: true
+      summary: false
       members:
         - init_chat_model

reference/python/docs/langchain_core/documents.md

@@ -1,3 +1,6 @@
-::: langchain_core.documents.base.BaseMedia
-::: langchain_core.documents.base.Blob
+::: langchain_core.documents
+    options:
+      members: []
 ::: langchain_core.documents.base.Document
+::: langchain_core.documents.base.Blob
+::: langchain_core.documents.base.BaseMedia

reference/python/docs/langchain_core/language_models.md

@@ -1,8 +1,5 @@
 <!-- `members: []` in order to show module docstring -->
 ::: langchain_core.language_models
-    options:
-      members: []
-::: langchain_core.language_models.chat_models
     options:
       parameter_headings: true
       show_inheritance_diagram: true

reference/python/mkdocs.yml

@@ -228,6 +228,7 @@ plugins:
               # Preload modules before collecting documentation to enable cross-references
               - langchain
               - langchain_core
+              - langgraph
               - langsmith
 
             # Generate objects.inv file for this site to enable cross-referencing from other sites

reference/python/uv.lock

@@ -936,9 +936,9 @@ Existing functionality outside the focus of standard interfaces and agents has b
 
 Methods, functions, and other objects that were already deprecated and slated for removal in 1.0 have been deleted. Check the [deprecation notices](https://python.langchain.com/docs/versions/migrating_chains) from previous versions for replacement APIs.
 
-### `.text()` is now a property
+### Text property
 
-Use of the `.text()` method on message objects should drop the parentheses:
+Use of the `.text()` method on message objects should drop the parentheses, as it is now a property:
 
 ```python
 # Property access
@@ -948,4 +948,16 @@ text = response.text
 text = response.text()
 ```
 
-Existing usage patterns (i.e., `.text()`) will continue to function but now emit a warning.
+Existing usage patterns (i.e., `.text()`) will continue to function but now emit a warning. The method form will be removed in v2.
+
+### `example` parameter removed from `AIMessage`
+
+The `example` parameter has been removed from @[`AIMessage`] objects. We recommend migrating to use `additional_kwargs` for passing extra metadata as needed.
+
+## Minor changes
+
+- `AIMessageChunk` objects now include a `chunk_position` attribute with position `'last'` to indicate the final chunk in a stream. This allows for clearer handling of streamed messages. If the chunk is not the final one, `chunk_position` will be `None`.
+- `LanguageModelOutputVar` is now typed to @[`AIMessage`] instead of @[`BaseMessage`].
+- The logic for merging message chunks (`AIMessageChunk.add`) has been updated with more sophisticated selection handling for the final id for the merged chunk. It prioritizes provider-assigned IDs over LangChain-generated IDs.
+- We now open files with `utf-8` encoding by default.
+- Standard tests now use multimodal content blocks.