Merge latest main and fix a few tests

.github/workflows/backend_integration_tests.yml

@@ -3,7 +3,6 @@ name: Backend - Integration tests
 on:
   push:
     branches: [main]
-  merge_group: {}
 
 jobs:
   pytest:

.github/workflows/backend_unit_tests.yml

@@ -4,7 +4,6 @@ on:
   push:
     branches: [main]
   pull_request: {}
-  merge_group: {}
 
 jobs:
   pytest:

.github/workflows/frontend_assistants_web_tests.yml

@@ -6,7 +6,6 @@ on:
     paths:
       - src/interfaces/assistants_web/**
   pull_request: {}
-  merge_group: {}
 
 jobs:
   interface_tests:

.github/workflows/frontend_coral_web_tests.yml

@@ -6,7 +6,6 @@ on:
     paths:
       - src/interfaces/coral_web/**
   pull_request: {}
-  merge_group: {}
 
 jobs:
   interface_tests:

.github/workflows/frontend_slack_bot_tests.yml

@@ -6,7 +6,6 @@ on:
     paths:
       - src/interfaces/slack_bot/**
   pull_request: {}
-  merge_group: {}
 
 jobs:
   interface_tests:

Makefile

@@ -16,7 +16,7 @@ down:
 
 .PHONY: run-unit-tests
 run-unit-tests:
-	poetry run pytest src/backend/tests/unit --cov=src/backend --cov-report=xml
+	poetry run pytest src/backend/tests/unit/$(file) --cov=src/backend --cov-report=xml
 
 .PHONY: run-community-tests
 run-community-tests:

docs/config_details/config_description.md

@@ -23,8 +23,6 @@
   - redis - Redis configurations
      - url - URL of the redis, for example, redis://:redis@redis:6379
   - tools - Tool configurations
-     - enabled_tools - these are the tools that are enabled for the toolkit. The full list of tools can be found in the src/backend/config/tools.py file.
-       The community tools are listed in the src/community/config/tools.py file. Please note that the tools availability is checked too.
      - python_interpreter - Python interpreter configurations
        - url - URL of the python interpreter tool
   - feature_flags - Feature flags configurations

docs/custom_tool_guides/slack.md

@@ -47,7 +47,7 @@ SLACK_CLIENT_SECRET=<your_client_secret from step 1>
 
 ## 4. Enable the Slack Tool in the Frontend
 
-To enable the Slack tool in the frontend, you will need to modify the `src/community/config/tools.py` file. Add the `TOOL_SLACK_ID` to the `AGENT_SETTINGS_TOOLS` list.
+To enable the Slack tool in the frontend, you will need to modify the `src/interfaces/assistants_web/src/constants/tools.ts` file. Add the `TOOL_SLACK_ID` to the `AGENT_SETTINGS_TOOLS` list.
 
 ```typescript
 export const AGENT_SETTINGS_TOOLS = [
@@ -58,7 +58,7 @@ export const AGENT_SETTINGS_TOOLS = [
 ];
 ```
 
-To enable the Slack tool in the frontend for Base Agent, you will need to modify the `src/community/config/tools.py` file. Remove the `TOOL_SLACK_ID` from the `BASE_AGENT_EXCLUDED_TOOLS` list.
+To enable the Slack tool in the frontend for Base Agent, you will need to modify the `src/interfaces/assistants_web/src/constants/tools.ts` file. Remove the `TOOL_SLACK_ID` from the `BASE_AGENT_EXCLUDED_TOOLS` list.
 By default, the Slack Tool is disabled for the Base Agent. Also if you need to exclude some tool from the Base Agent just add it to the `BASE_AGENT_EXCLUDED_TOOLS` list.
 ```typescript
 export const BASE_AGENT_EXCLUDED_TOOLS = [];

docs/custom_tool_guides/tool_guide.md

@@ -53,7 +53,7 @@ from community.tools import BaseTool
 
 
 class ArxivRetriever(BaseTool):
-    NAME = "arxiv"
+    ID = "arxiv"
 
     def __init__(self):
         self.client = ArxivAPIWrapper()
@@ -64,6 +64,27 @@ class ArxivRetriever(BaseTool):
     def is_available(cls) -> bool:
         return True
 
+    @classmethod
+    # You will need to add a tool definition here
+    def get_tool_definition(cls) -> ToolDefinition:
+        return ToolDefinition(
+            name=cls.ID,    
+            display_name="Arxiv",
+            implementation=cls,
+            parameter_definitions={
+                "query": {
+                    "description": "Query for retrieval.",
+                    "type": "str",
+                    "required": True,
+                }
+            },
+            is_visible=False,
+            is_available=cls.is_available(),
+            error_message=cls.generate_error_message(),
+            category=ToolCategory.DataLoader,
+            description="Retrieves documents from Arxiv.",
+        )
+
     # Your tool needs to implement this call() method
     def call(self, parameters: str, **kwargs: Any) -> List[Dict[str, Any]]:
         result = self.client.run(parameters)
@@ -84,34 +105,9 @@ return [{"text": "The fox is blue", "url": "wikipedia.org/foxes", "title": "Colo
 
 Next, add your tool class to the init file by locating it in `src/community/tools/__init__.py`. Import your tool here, then add it to the `__all__` list.
 
-To enable your tool, you will need to go to the `configuration.yaml` file and add your tool's name to the list of `enabled_tools`. This tool name will correspond to the one defined in the `NAME` attribute of your class.
-
 Finally, you will need to add your tool definition to the config file. Locate it in `src/community/config/tools.py`, and import your tool at the top with `from backend.tools import ..`. 
 
-In the ToolName enum, add your tool as an enum value. For example, `My_Tool = MyTool.NAME`.
-
-In the `ALL_TOOLS` dictionary, add your tool definition. This should look like:
-
-```python
-    ToolName.My_Tool: ManagedTool(  # THE TOOLNAME HERE CORRESPONDS TO THE ENUM YOU DEFINED EARLIER
-        display_name="My Tool",
-        implementation=MyTool, # THIS IS THE CLASS YOU IMPORTED AT THE TOP
-        parameter_definitions={ # THESE ARE PARAMS THE MODEL WILL SEND TO YOUR TOOL, ADJUST AS NEEDED
-            "query": {
-                "description": "Query to search with",
-                "type": "str",
-                "required": True,
-            }
-        },
-        is_visible=True, 
-        is_available=MyTool.is_available(), 
-        auth_implementation=None, # EMPTY IF NO AUTH NEEDED
-        error_message="Something went wrong",
-        category=Category.DataLoader,  # CHECK CATEGORY ENUM FOR POSSIBLE VALUES
-        description="An example definition to get you started.",
-    ),
-```
-
+Finally, to enable your tool, add your tool as an enum value. For example, `My_Tool = MyToolClass`.
 
 ## Step 5: Test Your Tool!
 

docs/how_to_guides.md

@@ -48,7 +48,7 @@ The core chat interface is the Coral frontend. To implement your own interface:
 If you have already created a [connector](https://docs.cohere.com/docs/connectors), you can utilize it within the toolkit by following these steps:
 
 1. Configure your connector using `ConnectorRetriever`.
-2. Add its definition in [community/config/tools.py](https://github.com/cohere-ai/cohere-toolkit/blob/main/src/community/config/tools.py), following the `Arxiv` implementation, using the category `Category.DataLoader`.
+2. Add its definition in [community/config/tools.py](https://github.com/cohere-ai/cohere-toolkit/blob/main/src/community/config/tools.py), following the `Arxiv` implementation, using the category `ToolCategory.DataLoader`.
 
 You can now use both the Coral frontend and API with your connector.