core[minor], ...: add tool calls message (#18947)

core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor]

```python
class ToolCall(TypedDict):
    name: str
    args: Dict[str, Any]
    id: Optional[str]

class InvalidToolCall(TypedDict):
    name: Optional[str]
    args: Optional[str]
    id: Optional[str]
    error: Optional[str]

class ToolCallChunk(TypedDict):
    name: Optional[str]
    args: Optional[str]
    id: Optional[str]
    index: Optional[int]


class AIMessage(BaseMessage):
    ...
    tool_calls: List[ToolCall] = []
    invalid_tool_calls: List[InvalidToolCall] = []
    ...


class AIMessageChunk(AIMessage, BaseMessageChunk):
    ...
    tool_call_chunks: Optional[List[ToolCallChunk]] = None
    ...
```
Important considerations:
- Parsing logic occurs within different providers;
- ~Changing output type is a breaking change for anyone doing explicit
type checking;~
- ~Langsmith rendering will need to be updated:
https://github.com/langchain-ai/langchainplus/pull/3561~
- ~Langserve will need to be updated~
- Adding chunks:
- ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has
non-null .tool_calls.~
- Tool call chunks are appended, merging when having equal values of
`index`.
  - additional_kwargs accumulate the normal way.
- During streaming:
- ~Messages can change types (e.g., from AIMessageChunk to
AIToolCallsMessageChunk)~
- Output parsers parse additional_kwargs (during .invoke they read off
tool calls).

Packages outside of `partners/`:
- https://github.com/langchain-ai/langchain-cohere/pull/7
- https://github.com/langchain-ai/langchain-google/pull/123/files

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>

libs/partners/openai/langchain_openai/chat_models/base.py

@@ -63,6 +63,8 @@ from langchain_core.output_parsers.base import OutputParserLike
 from langchain_core.output_parsers.openai_tools import (
     JsonOutputKeyToolsParser,
     PydanticToolsParser,
+    make_invalid_tool_call,
+    parse_tool_call,
 )
 from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
 from langchain_core.pydantic_v1 import BaseModel, Field, SecretStr, root_validator
@@ -103,10 +105,24 @@ def _convert_dict_to_message(_dict: Mapping[str, Any]) -> BaseMessage:
         additional_kwargs: Dict = {}
         if function_call := _dict.get("function_call"):
             additional_kwargs["function_call"] = dict(function_call)
-        if tool_calls := _dict.get("tool_calls"):
-            additional_kwargs["tool_calls"] = tool_calls
+        tool_calls = []
+        invalid_tool_calls = []
+        if raw_tool_calls := _dict.get("tool_calls"):
+            additional_kwargs["tool_calls"] = raw_tool_calls
+            for raw_tool_call in raw_tool_calls:
+                try:
+                    tool_calls.append(parse_tool_call(raw_tool_call, return_id=True))
+                except Exception as e:
+                    invalid_tool_calls.append(
+                        make_invalid_tool_call(raw_tool_call, str(e))
+                    )
         return AIMessage(
-            content=content, additional_kwargs=additional_kwargs, name=name, id=id_
+            content=content,
+            additional_kwargs=additional_kwargs,
+            name=name,
+            id=id_,
+            tool_calls=tool_calls,
+            invalid_tool_calls=invalid_tool_calls,
         )
     elif role == "system":
         return SystemMessage(content=_dict.get("content", ""), name=name, id=id_)
@@ -188,14 +204,30 @@ def _convert_delta_to_message_chunk(
         if "name" in function_call and function_call["name"] is None:
             function_call["name"] = ""
         additional_kwargs["function_call"] = function_call
-    if _dict.get("tool_calls"):
-        additional_kwargs["tool_calls"] = _dict["tool_calls"]
+    tool_call_chunks = []
+    if raw_tool_calls := _dict.get("tool_calls"):
+        additional_kwargs["tool_calls"] = raw_tool_calls
+        try:
+            tool_call_chunks = [
+                {
+                    "name": rtc["function"].get("name"),
+                    "args": rtc["function"].get("arguments"),
+                    "id": rtc.get("id"),
+                    "index": rtc["index"],
+                }
+                for rtc in raw_tool_calls
+            ]
+        except KeyError:
+            pass
 
     if role == "user" or default_class == HumanMessageChunk:
         return HumanMessageChunk(content=content, id=id_)
     elif role == "assistant" or default_class == AIMessageChunk:
         return AIMessageChunk(
-            content=content, additional_kwargs=additional_kwargs, id=id_
+            content=content,
+            additional_kwargs=additional_kwargs,
+            id=id_,
+            tool_call_chunks=tool_call_chunks,
         )
     elif role == "system" or default_class == SystemMessageChunk:
         return SystemMessageChunk(content=content, id=id_)