genai: update standard tests library (#705)

libs/genai/langchain_google_genai/chat_models.py

@@ -301,10 +301,12 @@ def _convert_to_parts(
     return parts
 
 
-def _convert_tool_message_to_part(message: ToolMessage | FunctionMessage) -> Part:
+def _convert_tool_message_to_part(
+    message: ToolMessage | FunctionMessage, name: Optional[str] = None
+) -> Part:
     """Converts a tool or function message to a google part."""
     # Legacy agent stores tool name in message.additional_kwargs instead of message.name
-    name = message.name or message.additional_kwargs.get("name")
+    name = message.name or name or message.additional_kwargs.get("name")
     response: Any
     if not isinstance(message.content, str):
         response = message.content
@@ -332,16 +334,17 @@ def _get_ai_message_tool_messages_parts(
     list of Parts.
     """
     # We are interested only in the tool messages that are part of the AI message
-    tool_calls_ids = [tool_call["id"] for tool_call in ai_message.tool_calls]
+    tool_calls_ids = {tool_call["id"]: tool_call for tool_call in ai_message.tool_calls}
     parts = []
     for i, message in enumerate(tool_messages):
         if not tool_calls_ids:
             break
         if message.tool_call_id in tool_calls_ids:
-            # remove the id from the list, so that we do not iterate over it again
-            tool_calls_ids.remove(message.tool_call_id)
-            part = _convert_tool_message_to_part(message)
+            tool_call = tool_calls_ids[message.tool_call_id]
+            part = _convert_tool_message_to_part(message, name=tool_call.get("name"))
             parts.append(part)
+            # remove the id from the dict, so that we do not iterate over it again
+            tool_calls_ids.pop(message.tool_call_id)
     return parts
 
 
@@ -361,8 +364,14 @@ def _parse_chat_history(
         message for message in input_messages if isinstance(message, ToolMessage)
     ]
     for i, message in enumerate(messages_without_tool_messages):
-        if i == 0 and isinstance(message, SystemMessage):
-            system_instruction = Content(parts=_convert_to_parts(message.content))
+        if isinstance(message, SystemMessage):
+            system_parts = _convert_to_parts(message.content)
+            if i == 0:
+                system_instruction = Content(parts=system_parts)
+            elif system_instruction is not None:
+                system_instruction.parts.extend(system_parts)
+            else:
+                pass
             continue
         elif isinstance(message, AIMessage):
             role = "model"

libs/genai/pyproject.toml

@@ -12,7 +12,7 @@ license = "MIT"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-langchain-core = "^0.3.27"
+langchain-core = "^0.3.35"
 google-generativeai = "^0.8.0"
 pydantic = ">=2,<3"
 filetype = "^1.2.0"
@@ -28,41 +28,33 @@ syrupy = "^4.0.2"
 pytest-watcher = "^0.3.4"
 pytest-asyncio = "^0.21.1"
 numpy = "^1.26.2"
-langchain-tests = "0.3.1"
+langchain-tests = "0.3.12"
 
 [tool.codespell]
 ignore-words-list = "rouge"
 
 
-
-
 [tool.poetry.group.codespell]
 optional = true
 
 [tool.poetry.group.codespell.dependencies]
 codespell = "^2.2.0"
 
 
-
-
 [tool.poetry.group.test_integration]
 optional = true
 
 [tool.poetry.group.test_integration.dependencies]
 pytest = "^7.3.0"
 
 
-
-
 [tool.poetry.group.lint]
 optional = true
 
 [tool.poetry.group.lint.dependencies]
 ruff = "^0.1.5"
 
 
-
-
 [tool.poetry.group.typing.dependencies]
 mypy = "^1.10"
 types-requests = "^2.28.11.5"
@@ -71,8 +63,6 @@ types-protobuf = "^4.24.0.20240302"
 numpy = "^1.26.2"
 
 
-
-
 [tool.poetry.group.dev]
 optional = true
 

libs/genai/tests/integration_tests/test_standard.py

@@ -6,7 +6,8 @@
 from langchain_core.language_models import BaseChatModel
 from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
 from langchain_core.rate_limiters import InMemoryRateLimiter
-from langchain_standard_tests.integration_tests import ChatModelIntegrationTests
+from langchain_core.tools import BaseTool
+from langchain_tests.integration_tests import ChatModelIntegrationTests
 
 from langchain_google_genai import ChatGoogleGenerativeAI
 
@@ -26,18 +27,30 @@ def chat_model_params(self) -> dict:
             "rate_limiter": rate_limiter_2_0,
         }
 
+    @pytest.mark.xfail(
+        reason="Likely a bug in genai: prompt_token_count inconsistent in final chunk."
+    )
+    def test_usage_metadata_streaming(self, model: BaseChatModel) -> None:
+        super().test_usage_metadata_streaming(model)
+
     @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
-    async def test_structured_output_async(self, model: BaseChatModel) -> None:
-        await super().test_structured_output_async(model)
+    async def test_structured_output_async(
+        self, model: BaseChatModel, schema_type: str
+    ) -> None:
+        await super().test_structured_output_async(model, schema_type)
 
     @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
-    def test_structured_output(self, model: BaseChatModel) -> None:
-        super().test_structured_output(model)
+    def test_structured_output(self, model: BaseChatModel, schema_type: str) -> None:
+        super().test_structured_output(model, schema_type)
 
     @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
     def test_structured_output_pydantic_2_v1(self, model: BaseChatModel) -> None:
         super().test_structured_output_pydantic_2_v1(model)
 
+    @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
+    def test_structured_output_optional_param(self, model: BaseChatModel) -> None:
+        super().test_structured_output_optional_param(model)
+
     @pytest.mark.xfail(reason="investigate")
     def test_bind_runnables_as_tools(self, model: BaseChatModel) -> None:
         super().test_bind_runnables_as_tools(model)
@@ -56,20 +69,28 @@ def chat_model_params(self) -> dict:
         }
 
     @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
-    async def test_structured_output_async(self, model: BaseChatModel) -> None:
-        await super().test_structured_output_async(model)
+    async def test_structured_output_async(
+        self, model: BaseChatModel, schema_type: str
+    ) -> None:
+        await super().test_structured_output_async(model, schema_type)
 
     @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
-    def test_structured_output(self, model: BaseChatModel) -> None:
-        super().test_structured_output(model)
+    def test_structured_output(self, model: BaseChatModel, schema_type: str) -> None:
+        super().test_structured_output(model, schema_type)
 
     @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
     def test_structured_output_pydantic_2_v1(self, model: BaseChatModel) -> None:
         super().test_structured_output_pydantic_2_v1(model)
 
+    @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
+    def test_structured_output_optional_param(self, model: BaseChatModel) -> None:
+        super().test_structured_output_optional_param(model)
+
     @pytest.mark.xfail(reason="Not yet supported")
-    def test_tool_message_histories_list_content(self, model: BaseChatModel) -> None:
-        super().test_tool_message_histories_list_content(model)
+    def test_tool_message_histories_list_content(
+        self, model: BaseChatModel, my_adder_tool: BaseTool
+    ) -> None:
+        super().test_tool_message_histories_list_content(model, my_adder_tool)
 
     @property
     def supported_usage_metadata_details(

libs/genai/tests/unit_tests/test_standard.py

@@ -1,7 +1,7 @@
 from typing import Tuple, Type
 
 from langchain_core.language_models import BaseChatModel
-from langchain_standard_tests.unit_tests import ChatModelUnitTests
+from langchain_tests.unit_tests import ChatModelUnitTests
 
 from langchain_google_genai import ChatGoogleGenerativeAI