langchain-core 1.0.0a8__py3-none-any.whl → 1.0.0rc2__py3-none-any.whl

langchain_core/messages/ai.py

@@ -40,13 +40,13 @@ class InputTokenDetails(TypedDict, total=False):
     Does *not* need to sum to full input token count. Does *not* need to have all keys.
 
     Example:
-        .. code-block:: python
-
-            {
-                "audio": 10,
-                "cache_creation": 200,
-                "cache_read": 100,
-            }
+        ```python
+        {
+            "audio": 10,
+            "cache_creation": 200,
+            "cache_read": 100,
+        }
+        ```
 
     !!! version-added "Added in version 0.3.9"
 
@@ -76,12 +76,12 @@ class OutputTokenDetails(TypedDict, total=False):
     Does *not* need to sum to full output token count. Does *not* need to have all keys.
 
     Example:
-        .. code-block:: python
-
-            {
-                "audio": 10,
-                "reasoning": 200,
-            }
+        ```python
+        {
+            "audio": 10,
+            "reasoning": 200,
+        }
+        ```
 
     !!! version-added "Added in version 0.3.9"
 
@@ -104,25 +104,25 @@ class UsageMetadata(TypedDict):
     This is a standard representation of token usage that is consistent across models.
 
     Example:
-        .. code-block:: python
-
-            {
-                "input_tokens": 350,
-                "output_tokens": 240,
-                "total_tokens": 590,
-                "input_token_details": {
-                    "audio": 10,
-                    "cache_creation": 200,
-                    "cache_read": 100,
-                },
-                "output_token_details": {
-                    "audio": 10,
-                    "reasoning": 200,
-                },
-            }
+        ```python
+        {
+            "input_tokens": 350,
+            "output_tokens": 240,
+            "total_tokens": 590,
+            "input_token_details": {
+                "audio": 10,
+                "cache_creation": 200,
+                "cache_read": 100,
+            },
+            "output_token_details": {
+                "audio": 10,
+                "reasoning": 200,
+            },
+        }
+        ```
 
     !!! warning "Behavior changed in 0.3.9"
-        Added ``input_token_details`` and ``output_token_details``.
+        Added `input_token_details` and `output_token_details`.
 
     """
 
@@ -148,27 +148,26 @@ class UsageMetadata(TypedDict):
 class AIMessage(BaseMessage):
     """Message from an AI.
 
-    AIMessage is returned from a chat model as a response to a prompt.
+    An `AIMessage` is returned from a chat model as a response to a prompt.
 
     This message represents the output of the model and consists of both
-    the raw output as returned by the model together standardized fields
+    the raw output as returned by the model and standardized fields
     (e.g., tool calls, usage metadata) added by the LangChain framework.
 
     """
 
     tool_calls: list[ToolCall] = []
-    """If provided, tool calls associated with the message."""
+    """If present, tool calls associated with the message."""
     invalid_tool_calls: list[InvalidToolCall] = []
-    """If provided, tool calls with parsing errors associated with the message."""
+    """If present, tool calls with parsing errors associated with the message."""
     usage_metadata: UsageMetadata | None = None
-    """If provided, usage metadata for a message, such as token counts.
+    """If present, usage metadata for a message, such as token counts.
 
     This is a standard representation of token usage that is consistent across models.
-
     """
 
     type: Literal["ai"] = "ai"
-    """The type of the message (used for deserialization). Defaults to "ai"."""
+    """The type of the message (used for deserialization)."""
 
     @overload
     def __init__(
@@ -191,14 +190,14 @@ class AIMessage(BaseMessage):
         content_blocks: list[types.ContentBlock] | None = None,
         **kwargs: Any,
     ) -> None:
-        """Initialize ``AIMessage``.
+        """Initialize an `AIMessage`.
 
-        Specify ``content`` as positional arg or ``content_blocks`` for typing.
+        Specify `content` as positional arg or `content_blocks` for typing.
 
         Args:
             content: The content of the message.
             content_blocks: Typed standard content.
-            kwargs: Additional arguments to pass to the parent class.
+            **kwargs: Additional arguments to pass to the parent class.
         """
         if content_blocks is not None:
             # If there are tool calls in content_blocks, but not in tool_calls, add them
@@ -217,7 +216,11 @@ class AIMessage(BaseMessage):
 
     @property
     def lc_attributes(self) -> dict:
-        """Attrs to be serialized even if they are derived from other init args."""
+        """Attributes to be serialized.
+
+        Includes all attributes, even if they are derived from other initialization
+        arguments.
+        """
         return {
             "tool_calls": self.tool_calls,
             "invalid_tool_calls": self.invalid_tool_calls,
@@ -225,11 +228,11 @@ class AIMessage(BaseMessage):
 
     @property
     def content_blocks(self) -> list[types.ContentBlock]:
-        """Return content blocks of the message.
+        """Return standard, typed `ContentBlock` dicts from the message.
 
         If the message has a known model provider, use the provider-specific translator
         first before falling back to best-effort parsing. For details, see the property
-        on ``BaseMessage``.
+        on `BaseMessage`.
         """
         if self.response_metadata.get("output_version") == "v1":
             return cast("list[types.ContentBlock]", self.content)
@@ -331,11 +334,10 @@ class AIMessage(BaseMessage):
 
     @override
     def pretty_repr(self, html: bool = False) -> str:
-        """Return a pretty representation of the message.
+        """Return a pretty representation of the message for display.
 
         Args:
             html: Whether to return an HTML-formatted string.
-                 Defaults to False.
 
         Returns:
             A pretty representation of the message.
@@ -372,31 +374,27 @@ class AIMessage(BaseMessage):
 
 
 class AIMessageChunk(AIMessage, BaseMessageChunk):
-    """Message chunk from an AI."""
+    """Message chunk from an AI (yielded when streaming)."""
 
     # Ignoring mypy re-assignment here since we're overriding the value
     # to make sure that the chunk variant can be discriminated from the
     # non-chunk variant.
     type: Literal["AIMessageChunk"] = "AIMessageChunk"  # type: ignore[assignment]
-    """The type of the message (used for deserialization).
-
-    Defaults to ``AIMessageChunk``.
-
-    """
+    """The type of the message (used for deserialization)."""
 
     tool_call_chunks: list[ToolCallChunk] = []
     """If provided, tool call chunks associated with the message."""
 
     chunk_position: Literal["last"] | None = None
-    """Optional span represented by an aggregated AIMessageChunk.
+    """Optional span represented by an aggregated `AIMessageChunk`.
 
-    If a chunk with ``chunk_position="last"`` is aggregated into a stream,
-    ``tool_call_chunks`` in message content will be parsed into ``tool_calls``.
+    If a chunk with `chunk_position="last"` is aggregated into a stream,
+    `tool_call_chunks` in message content will be parsed into `tool_calls`.
     """
 
     @property
     def lc_attributes(self) -> dict:
-        """Attrs to be serialized even if they are derived from other init args."""
+        """Attributes to be serialized, even if they are derived from other initialization args."""  # noqa: E501
         return {
             "tool_calls": self.tool_calls,
             "invalid_tool_calls": self.invalid_tool_calls,
@@ -404,7 +402,7 @@ class AIMessageChunk(AIMessage, BaseMessageChunk):
 
     @property
     def content_blocks(self) -> list[types.ContentBlock]:
-        """Return content blocks of the message."""
+        """Return standard, typed `ContentBlock` dicts from the message."""
         if self.response_metadata.get("output_version") == "v1":
             return cast("list[types.ContentBlock]", self.content)
 
@@ -545,12 +543,15 @@ class AIMessageChunk(AIMessage, BaseMessageChunk):
                     and call_id in id_to_tc
                 ):
                     self.content[idx] = cast("dict[str, Any]", id_to_tc[call_id])
+                    if "extras" in block:
+                        # mypy does not account for instance check for dict above
+                        self.content[idx]["extras"] = block["extras"]  # type: ignore[index]
 
         return self
 
     @model_validator(mode="after")
     def init_server_tool_calls(self) -> Self:
-        """Parse server_tool_call_chunks."""
+        """Parse `server_tool_call_chunks`."""
         if (
             self.chunk_position == "last"
             and self.response_metadata.get("output_version") == "v1"
@@ -596,14 +597,14 @@ class AIMessageChunk(AIMessage, BaseMessageChunk):
 def add_ai_message_chunks(
     left: AIMessageChunk, *others: AIMessageChunk
 ) -> AIMessageChunk:
-    """Add multiple ``AIMessageChunk``s together.
+    """Add multiple `AIMessageChunk`s together.
 
     Args:
-        left: The first ``AIMessageChunk``.
-        *others: Other ``AIMessageChunk``s to add.
+        left: The first `AIMessageChunk`.
+        *others: Other `AIMessageChunk`s to add.
 
     Returns:
-        The resulting ``AIMessageChunk``.
+        The resulting `AIMessageChunk`.
 
     """
     content = merge_content(left.content, *(o.content for o in others))
@@ -681,43 +682,42 @@ def add_usage(left: UsageMetadata | None, right: UsageMetadata | None) -> UsageM
     """Recursively add two UsageMetadata objects.
 
     Example:
-        .. code-block:: python
-
-            from langchain_core.messages.ai import add_usage
-
-            left = UsageMetadata(
-                input_tokens=5,
-                output_tokens=0,
-                total_tokens=5,
-                input_token_details=InputTokenDetails(cache_read=3),
-            )
-            right = UsageMetadata(
-                input_tokens=0,
-                output_tokens=10,
-                total_tokens=10,
-                output_token_details=OutputTokenDetails(reasoning=4),
-            )
+        ```python
+        from langchain_core.messages.ai import add_usage
+
+        left = UsageMetadata(
+            input_tokens=5,
+            output_tokens=0,
+            total_tokens=5,
+            input_token_details=InputTokenDetails(cache_read=3),
+        )
+        right = UsageMetadata(
+            input_tokens=0,
+            output_tokens=10,
+            total_tokens=10,
+            output_token_details=OutputTokenDetails(reasoning=4),
+        )
 
-            add_usage(left, right)
+        add_usage(left, right)
+        ```
 
         results in
 
-        .. code-block:: python
-
-            UsageMetadata(
-                input_tokens=5,
-                output_tokens=10,
-                total_tokens=15,
-                input_token_details=InputTokenDetails(cache_read=3),
-                output_token_details=OutputTokenDetails(reasoning=4),
-            )
-
+        ```python
+        UsageMetadata(
+            input_tokens=5,
+            output_tokens=10,
+            total_tokens=15,
+            input_token_details=InputTokenDetails(cache_read=3),
+            output_token_details=OutputTokenDetails(reasoning=4),
+        )
+        ```
     Args:
-        left: The first ``UsageMetadata`` object.
-        right: The second ``UsageMetadata`` object.
+        left: The first `UsageMetadata` object.
+        right: The second `UsageMetadata` object.
 
     Returns:
-        The sum of the two ``UsageMetadata`` objects.
+        The sum of the two `UsageMetadata` objects.
 
     """
     if not (left or right):
@@ -740,48 +740,47 @@ def add_usage(left: UsageMetadata | None, right: UsageMetadata | None) -> UsageM
 def subtract_usage(
     left: UsageMetadata | None, right: UsageMetadata | None
 ) -> UsageMetadata:
-    """Recursively subtract two ``UsageMetadata`` objects.
+    """Recursively subtract two `UsageMetadata` objects.
 
-    Token counts cannot be negative so the actual operation is ``max(left - right, 0)``.
+    Token counts cannot be negative so the actual operation is `max(left - right, 0)`.
 
     Example:
-        .. code-block:: python
-
-            from langchain_core.messages.ai import subtract_usage
-
-            left = UsageMetadata(
-                input_tokens=5,
-                output_tokens=10,
-                total_tokens=15,
-                input_token_details=InputTokenDetails(cache_read=4),
-            )
-            right = UsageMetadata(
-                input_tokens=3,
-                output_tokens=8,
-                total_tokens=11,
-                output_token_details=OutputTokenDetails(reasoning=4),
-            )
+        ```python
+        from langchain_core.messages.ai import subtract_usage
+
+        left = UsageMetadata(
+            input_tokens=5,
+            output_tokens=10,
+            total_tokens=15,
+            input_token_details=InputTokenDetails(cache_read=4),
+        )
+        right = UsageMetadata(
+            input_tokens=3,
+            output_tokens=8,
+            total_tokens=11,
+            output_token_details=OutputTokenDetails(reasoning=4),
+        )
 
-            subtract_usage(left, right)
+        subtract_usage(left, right)
+        ```
 
         results in
 
-        .. code-block:: python
-
-            UsageMetadata(
-                input_tokens=2,
-                output_tokens=2,
-                total_tokens=4,
-                input_token_details=InputTokenDetails(cache_read=4),
-                output_token_details=OutputTokenDetails(reasoning=0),
-            )
-
+        ```python
+        UsageMetadata(
+            input_tokens=2,
+            output_tokens=2,
+            total_tokens=4,
+            input_token_details=InputTokenDetails(cache_read=4),
+            output_token_details=OutputTokenDetails(reasoning=0),
+        )
+        ```
     Args:
-        left: The first ``UsageMetadata`` object.
-        right: The second ``UsageMetadata`` object.
+        left: The first `UsageMetadata` object.
+        right: The second `UsageMetadata` object.
 
     Returns:
-        The resulting ``UsageMetadata`` after subtraction.
+        The resulting `UsageMetadata` after subtraction.
 
     """
     if not (left or right):

langchain_core/messages/base.py

@@ -48,13 +48,13 @@ class TextAccessor(str):
 
     Exists to maintain backward compatibility while transitioning from method-based to
     property-based text access in message objects. In LangChain <v1.0, message text was
-    accessed via ``.text()`` method calls. In v1.0=<, the preferred pattern is property
-    access via ``.text``.
+    accessed via `.text()` method calls. In v1.0=<, the preferred pattern is property
+    access via `.text`.
 
-    Rather than breaking existing code immediately, ``TextAccessor`` allows both
+    Rather than breaking existing code immediately, `TextAccessor` allows both
     patterns:
-    - Modern property access: ``message.text`` (returns string directly)
-    - Legacy method access: ``message.text()`` (callable, emits deprecation warning)
+    - Modern property access: `message.text` (returns string directly)
+    - Legacy method access: `message.text()` (callable, emits deprecation warning)
 
     """
 
@@ -67,12 +67,12 @@ class TextAccessor(str):
     def __call__(self) -> str:
         """Enable method-style text access for backward compatibility.
 
-        This method exists solely to support legacy code that calls ``.text()``
-        as a method. New code should use property access (``.text``) instead.
+        This method exists solely to support legacy code that calls `.text()`
+        as a method. New code should use property access (`.text`) instead.
 
         !!! deprecated
-            As of `langchain-core` 1.0.0, calling ``.text()`` as a method is deprecated.
-            Use ``.text`` as a property instead. This method will be removed in 2.0.0.
+            As of `langchain-core` 1.0.0, calling `.text()` as a method is deprecated.
+            Use `.text` as a property instead. This method will be removed in 2.0.0.
 
         Returns:
             The string content, identical to property access.
@@ -92,11 +92,11 @@ class TextAccessor(str):
 class BaseMessage(Serializable):
     """Base abstract message class.
 
-    Messages are the inputs and outputs of a ``ChatModel``.
+    Messages are the inputs and outputs of a chat model.
     """
 
     content: str | list[str | dict]
-    """The string contents of the message."""
+    """The contents of the message."""
 
     additional_kwargs: dict = Field(default_factory=dict)
     """Reserved for additional payload data associated with the message.
@@ -159,14 +159,14 @@ class BaseMessage(Serializable):
         content_blocks: list[types.ContentBlock] | None = None,
         **kwargs: Any,
     ) -> None:
-        """Initialize ``BaseMessage``.
+        """Initialize a `BaseMessage`.
 
-        Specify ``content`` as positional arg or ``content_blocks`` for typing.
+        Specify `content` as positional arg or `content_blocks` for typing.
 
         Args:
-            content: The string contents of the message.
+            content: The contents of the message.
             content_blocks: Typed standard content.
-            kwargs: Additional arguments to pass to the parent class.
+            **kwargs: Additional arguments to pass to the parent class.
         """
         if content_blocks is not None:
             super().__init__(content=content_blocks, **kwargs)
@@ -175,7 +175,7 @@ class BaseMessage(Serializable):
 
     @classmethod
     def is_lc_serializable(cls) -> bool:
-        """``BaseMessage`` is serializable.
+        """`BaseMessage` is serializable.
 
         Returns:
             True
@@ -184,10 +184,10 @@ class BaseMessage(Serializable):
 
     @classmethod
     def get_lc_namespace(cls) -> list[str]:
-        """Get the namespace of the langchain object.
+        """Get the namespace of the LangChain object.
 
         Returns:
-            ``["langchain", "schema", "messages"]``
+            `["langchain", "schema", "messages"]`
         """
         return ["langchain", "schema", "messages"]
 
@@ -259,11 +259,11 @@ class BaseMessage(Serializable):
     def text(self) -> TextAccessor:
         """Get the text content of the message as a string.
 
-        Can be used as both property (``message.text``) and method (``message.text()``).
+        Can be used as both property (`message.text`) and method (`message.text()`).
 
         !!! deprecated
-            As of langchain-core 1.0.0, calling ``.text()`` as a method is deprecated.
-            Use ``.text`` as a property instead. This method will be removed in 2.0.0.
+            As of `langchain-core` 1.0.0, calling `.text()` as a method is deprecated.
+            Use `.text` as a property instead. This method will be removed in 2.0.0.
 
         Returns:
             The text content of the message.
@@ -306,8 +306,8 @@ class BaseMessage(Serializable):
         """Get a pretty representation of the message.
 
         Args:
-            html: Whether to format the message as HTML. If True, the message will be
-                formatted with HTML tags. Default is False.
+            html: Whether to format the message as HTML. If `True`, the message will be
+                formatted with HTML tags.
 
         Returns:
             A pretty representation of the message.
@@ -331,8 +331,8 @@ def merge_content(
     """Merge multiple message contents.
 
     Args:
-        first_content: The first ``content``. Can be a string or a list.
-        contents: The other ``content``s. Can be a string or a list.
+        first_content: The first `content`. Can be a string or a list.
+        contents: The other `content`s. Can be a string or a list.
 
     Returns:
         The merged content.
@@ -388,9 +388,9 @@ class BaseMessageChunk(BaseMessage):
 
         For example,
 
-        ``AIMessageChunk(content="Hello") + AIMessageChunk(content=" World")``
+        `AIMessageChunk(content="Hello") + AIMessageChunk(content=" World")`
 
-        will give ``AIMessageChunk(content="Hello World")``
+        will give `AIMessageChunk(content="Hello World")`
 
         """
         if isinstance(other, BaseMessageChunk):
@@ -439,8 +439,8 @@ def message_to_dict(message: BaseMessage) -> dict:
         message: Message to convert.
 
     Returns:
-        Message as a dict. The dict will have a ``type`` key with the message type
-        and a ``data`` key with the message data as a dict.
+        Message as a dict. The dict will have a `type` key with the message type
+        and a `data` key with the message data as a dict.
 
     """
     return {"type": message.type, "data": message.model_dump()}
@@ -450,7 +450,7 @@ def messages_to_dict(messages: Sequence[BaseMessage]) -> list[dict]:
     """Convert a sequence of Messages to a list of dictionaries.
 
     Args:
-        messages: Sequence of messages (as ``BaseMessage``s) to convert.
+        messages: Sequence of messages (as `BaseMessage`s) to convert.
 
     Returns:
         List of messages as dicts.
@@ -464,7 +464,7 @@ def get_msg_title_repr(title: str, *, bold: bool = False) -> str:
 
     Args:
         title: The title.
-        bold: Whether to bold the title. Default is False.
+        bold: Whether to bold the title.
 
     Returns:
         The title representation.

langchain_core/messages/block_translators/__init__.py

@@ -1,13 +1,13 @@
 """Derivations of standard content blocks from provider content.
 
-``AIMessage`` will first attempt to use a provider-specific translator if
-``model_provider`` is set in ``response_metadata`` on the message. Consequently, each
+`AIMessage` will first attempt to use a provider-specific translator if
+`model_provider` is set in `response_metadata` on the message. Consequently, each
 provider translator must handle all possible content response types from the provider,
 including text.
 
 If no provider is set, or if the provider does not have a registered translator,
-``AIMessage`` will fall back to best-effort parsing of the content into blocks using
-the implementation in ``BaseMessage``.
+`AIMessage` will fall back to best-effort parsing of the content into blocks using
+the implementation in `BaseMessage`.
 """
 
 from __future__ import annotations
@@ -23,15 +23,15 @@ if TYPE_CHECKING:
 PROVIDER_TRANSLATORS: dict[str, dict[str, Callable[..., list[types.ContentBlock]]]] = {}
 """Map model provider names to translator functions.
 
-The dictionary maps provider names (e.g. ``'openai'``, ``'anthropic'``) to another
+The dictionary maps provider names (e.g. `'openai'`, `'anthropic'`) to another
 dictionary with two keys:
-- ``'translate_content'``: Function to translate ``AIMessage`` content.
-- ``'translate_content_chunk'``: Function to translate ``AIMessageChunk`` content.
+- `'translate_content'`: Function to translate `AIMessage` content.
+- `'translate_content_chunk'`: Function to translate `AIMessageChunk` content.
 
-When calling `.content_blocks` on an ``AIMessage`` or ``AIMessageChunk``, if
-``model_provider`` is set in ``response_metadata``, the corresponding translator
+When calling `content_blocks` on an `AIMessage` or `AIMessageChunk`, if
+`model_provider` is set in `response_metadata`, the corresponding translator
 functions will be used to parse the content into blocks. Otherwise, best-effort parsing
-in ``BaseMessage`` will be used.
+in `BaseMessage` will be used.
 """
 
 
@@ -43,9 +43,9 @@ def register_translator(
     """Register content translators for a provider in `PROVIDER_TRANSLATORS`.
 
     Args:
-        provider: The model provider name (e.g. ``'openai'``, ``'anthropic'``).
-        translate_content: Function to translate ``AIMessage`` content.
-        translate_content_chunk: Function to translate ``AIMessageChunk`` content.
+        provider: The model provider name (e.g. `'openai'`, `'anthropic'`).
+        translate_content: Function to translate `AIMessage` content.
+        translate_content_chunk: Function to translate `AIMessageChunk` content.
     """
     PROVIDER_TRANSLATORS[provider] = {
         "translate_content": translate_content,
@@ -62,9 +62,9 @@ def get_translator(
         provider: The model provider name.
 
     Returns:
-        Dictionary with ``'translate_content'`` and ``'translate_content_chunk'``
+        Dictionary with `'translate_content'` and `'translate_content_chunk'`
         functions, or None if no translator is registered for the provider. In such
-        case, best-effort parsing in ``BaseMessage`` will be used.
+        case, best-effort parsing in `BaseMessage` will be used.
     """
     return PROVIDER_TRANSLATORS.get(provider)
 
@@ -72,10 +72,10 @@ def get_translator(
 def _register_translators() -> None:
     """Register all translators in langchain-core.
 
-    A unit test ensures all modules in ``block_translators`` are represented here.
+    A unit test ensures all modules in `block_translators` are represented here.
 
     For translators implemented outside langchain-core, they can be registered by
-    calling ``register_translator`` from within the integration package.
+    calling `register_translator` from within the integration package.
     """
     from langchain_core.messages.block_translators.anthropic import (  # noqa: PLC0415
         _register_anthropic_translator,