Merge branch 'main' into kevin

SmartManoj · SmartManoj · commit 8bc8f525a602 · 2025-06-23T10:16:03.000+05:30
diff --git a/docs/docs.json b/docs/docs.json
@@ -104,8 +104,9 @@
             ]
           },
           {
-            "group": "Customization",
+            "group": "Customizations & Settings",
             "pages": [
+              "usage/common-settings",
               "usage/prompting/repository",
               {
                 "group": "Microagents",
diff --git a/docs/usage/cloud/cloud-ui.mdx b/docs/usage/cloud/cloud-ui.mdx
@@ -1,7 +1,7 @@
 ---
 title: Cloud UI
-description: The Cloud UI provides a web interface for interacting with OpenHands. This page explains how to use the
- OpenHands Cloud UI.
+description: The Cloud UI provides a web interface for interacting with OpenHands. This page provides references on
+ how to use the OpenHands Cloud UI.
 ---
 
 ## Landing Page
@@ -22,8 +22,9 @@ The Settings page allows you to:
 - [Install the OpenHands Slack app](/usage/cloud/slack-installation).
 - Set application settings like your preferred language, notifications and other preferences.
 - Add credits to your account.
-- Generate custom secrets.
-- Create API keys to work with OpenHands programmatically.
+- [Generate custom secrets](/usage/common-settings#secrets-management).
+- [Create API keys to work with OpenHands programmatically](/usage/cloud/cloud-api).
+- Change your email address.
 
 ## Key Features
 
diff --git a/docs/usage/cloud/slack-installation.mdx b/docs/usage/cloud/slack-installation.mdx
@@ -25,7 +25,7 @@ description: This guide walks you through installing the OpenHands Slack app.
 
   **Make sure your Slack workspace admin/owner has installed OpenHands Slack App first.**
 
-  Every user in the Slack workspace (including admins/owners) must link their Cloud OpenHands account to the OpenHands Slack App. To do this:
+  Every user in the Slack workspace (including admins/owners) must link their OpenHands Cloud account to the OpenHands Slack App. To do this:
   1. Visit [integrations settings](https://app.all-hands.dev/settings/integrations) in OpenHands Cloud.
   2. Click `Install OpenHands Slack App`.
   3. In the top right corner, select the workspace to install the OpenHands Slack app.
diff --git a/docs/usage/common-settings.mdx b/docs/usage/common-settings.mdx
@@ -0,0 +1,52 @@
+---
+title: OpenHands Settings
+description: Overview of some of the settings available in OpenHands.
+---
+
+## Openhands Cloud vs Running on Your Own
+
+There are some differences between the settings available in OpenHands Cloud and those available when running OpenHands
+on your own:
+* [OpenHands Cloud settings](/usage/cloud/cloud-ui#settings)
+* [Settings available when running on your own](/usage/how-to/gui-mode#settings)
+
+Refer to these pages for more detailed information.
+
+## Secrets Management
+
+OpenHands provides a secrets manager that allows you to securely store and manage sensitive information that can be
+accessed by the agent during runtime, such as API keys. These secrets are automatically exported as environment
+variables in the agent's runtime environment.
+
+### Accessing the Secrets Manager
+
+In the Settings page, navigate to the `Secrets` tab. Here, you'll see a list of all your existing custom secrets.
+
+### Adding a New Secret
+1. Click `Add a new secret`.
+2. Fill in the following fields:
+   - **Name**: A unique identifier for your secret (e.g., `AWS_ACCESS_KEY`). This will be the environment variable name.
+   - **Value**: The sensitive information you want to store.
+   - **Description** (optional): A brief description of what the secret is used for, which is also provided to the agent.
+3. Click `Add secret` to save.
+
+### Editing a Secret
+
+1. Click the `Edit` button next to the secret you want to modify.
+2. You can update the name and description of the secret.
+<Note>
+  For security reasons, you cannot view or edit the value of an existing secret. If you need to change the
+  value, delete the secret and create a new one.
+</Note>
+
+### Deleting a Secret
+
+1. Click the `Delete` button next to the secret you want to remove.
+2. Select `Confirm` to delete the secret.
+
+### Using Secrets in the Agent
+ - All custom secrets are automatically exported as environment variables in the agent's runtime environment.
+ - You can access them in your code using standard environment variable access methods
+   (e.g., `os.environ['SECRET_NAME']` in Python).
+ - Example: If you create a secret named `OPENAI_API_KEY`, you can access it in your code as
+   `process.env.OPENAI_API_KEY` in JavaScript or `os.environ['OPENAI_API_KEY']` in Python.
diff --git a/docs/usage/getting-started.mdx b/docs/usage/getting-started.mdx
@@ -1,6 +1,6 @@
 ---
 title: Start Building
-description: So you've [run OpenHands](./installation) and have [set up your LLM](./installation#setup). Now what?
+description: So you've [run OpenHands](/usage/installation). Now what?
 icon: code
 ---
 
diff --git a/docs/usage/how-to/gui-mode.mdx b/docs/usage/how-to/gui-mode.mdx
@@ -25,9 +25,9 @@ You can use the Settings page at any time to:
 - Setup the LLM provider and model for OpenHands.
 - [Setup the search engine](/usage/search-engine-setup).
 - [Configure MCP servers](/usage/mcp).
-- [Connect to GitHub](/usage/how-to/gui-mode#github-setup) and [connect to GitLab](/usage/how-to/gui-mode#gitlab-setup)
+- [Connect to GitHub](/usage/how-to/gui-mode#github-setup) and [connect to GitLab](/usage/how-to/gui-mode#gitlab-setup).
 - Set application settings like your preferred language, notifications and other preferences.
-- [Manage custom secrets](/usage/how-to/gui-mode#secrets-management).
+- [Manage custom secrets](/usage/common-settings#secrets-management).
 
 #### GitHub Setup
 
@@ -157,37 +157,6 @@ OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment if pro
 
 </AccordionGroup>
 
-
-#### Secrets Management
-
-OpenHands provides a secrets manager that allows you to securely store and manage sensitive information that can be accessed by the agent during runtime, such as API keys. These secrets are automatically exported as environment variables in the agent's runtime environment.
-
-1. **Accessing the Secrets Manager**:
-   - In the Settings page, navigate to the `Secrets` tab.
-   - You'll see a list of all your existing custom secrets (if any).
-
-2. **Adding a New Secret**:
-   - Click the `Add New Secret` button.
-   - Fill in the following fields:
-     - **Name**: A unique identifier for your secret (e.g., `AWS_ACCESS_KEY`). This will be the environment variable name.
-     - **Value**: The sensitive information you want to store.
-     - **Description** (optional): A brief description of what the secret is used for, which is also provided to the agent.
-   - Click `Add Secret` to save.
-
-3. **Editing a Secret**:
-   - Click the `Edit` button next to the secret you want to modify.
-   - You can update the name and description of the secret.
-   - Note: For security reasons, you cannot view or edit the value of an existing secret. If you need to change the value, delete the secret and create a new one.
-
-4. **Deleting a Secret**:
-   - Click the `Delete` button next to the secret you want to remove.
-   - Confirm the deletion when prompted.
-
-5. **Using Secrets in the Agent**:
-   - All custom secrets are automatically exported as environment variables in the agent's runtime environment.
-   - You can access them in your code using standard environment variable access methods (e.g., `os.environ['SECRET_NAME']` in Python).
-   - Example: If you create a secret named `OPENAI_API_KEY`, you can access it in your code as `process.env.OPENAI_API_KEY` in JavaScript or `os.environ['OPENAI_API_KEY']` in Python.
-
 #### Advanced Settings
 
 The `Advanced` settings allows configuration of additional LLM settings. Inside the Settings page, under the `LLM` tab,
@@ -208,11 +177,11 @@ section of the documentation.
 The status indicator located in the bottom left of the screen will cycle through a number of states as a new conversation
 is loaded. Typically these include:
 
-* `Disconnected` : The frontend is not connected to any conversation
+* `Disconnected` : The frontend is not connected to any conversation.
 * `Connecting` : The frontend is connecting a websocket to a conversation.
 * `Building Runtime...` : The server is building a runtime. This is typically in development mode only while building a docker image.
 * `Starting Runtime...` : The server is starting a new runtime instance - probably a new docker container or remote runtime.
-* `Initializing Agent...` : The server is starting the agent loop. (This step does not appear at present with Nested runtimes)
+* `Initializing Agent...` : The server is starting the agent loop (This step does not appear at present with Nested runtimes).
 * `Setting up workspace...` : Usually this means a `git clone ...` operation.
 * `Setting up git hooks` : Setting up the git pre commit hooks for the workspace.
 * `Agent is awaiting user input...` : Ready to go!
diff --git a/docs/usage/installation.mdx b/docs/usage/installation.mdx
@@ -1,6 +1,6 @@
 ---
 title: Quick Start
-description: Running OpenHands Cloud or running on your local system.
+description: Running OpenHands Cloud or running on your own.
 icon: rocket
 ---
 
diff --git a/openhands/cli/settings.py b/openhands/cli/settings.py
@@ -264,23 +264,28 @@ def provider_validator(x):
         if change_model:
             model_completer = FuzzyWordCompleter(provider_models)
 
-            # Define a validator function that prints an error message
+            # Define a validator function that allows custom models but shows a warning
             def model_validator(x):
-                is_valid = x in provider_models
-                if not is_valid:
+                # Allow any non-empty model name
+                if not x.strip():
+                    return False
+
+                # Show a warning for models not in the predefined list, but still allow them
+                if x not in provider_models:
                     print_formatted_text(
                         HTML(
-                            f'<grey>Invalid model selected for provider {provider}: {x}</grey>'
+                            f'<yellow>Warning: {x} is not in the predefined list for provider {provider}. '
+                            f'Make sure this model name is correct.</yellow>'
                         )
                     )
-                return is_valid
+                return True
 
             model = await get_validated_input(
                 session,
                 '(Step 2/3) Select LLM Model (TAB for options, CTRL-c to cancel): ',
                 completer=model_completer,
                 validator=model_validator,
-                error_message=f'Invalid model selected for provider {provider}',
+                error_message='Model name cannot be empty',
             )
         else:
             # Use the default model
diff --git a/openhands/server/conversation_manager/conversation_manager.py b/openhands/server/conversation_manager/conversation_manager.py
@@ -107,6 +107,10 @@ async def maybe_start_agent_loop(
     async def send_to_event_stream(self, connection_id: str, data: dict):
         """Send data to an event stream."""
 
+    @abstractmethod
+    async def send_event_to_conversation(self, sid: str, data: dict):
+        """Send an event to a conversation."""
+
     @abstractmethod
     async def disconnect_from_session(self, connection_id: str):
         """Disconnect from a session."""
diff --git a/openhands/server/conversation_manager/docker_nested_conversation_manager.py b/openhands/server/conversation_manager/docker_nested_conversation_manager.py
@@ -275,6 +275,18 @@ async def send_to_event_stream(self, connection_id: str, data: dict):
         # Not supported - clients should connect directly to the nested server!
         raise ValueError('unsupported_operation')
 
+    async def send_event_to_conversation(self, sid, data):
+        async with httpx.AsyncClient(
+            headers={
+                'X-Session-API-Key': self._get_session_api_key_for_conversation(sid)
+            }
+        ) as client:
+            nested_url = self._get_nested_url(sid)
+            response = await client.post(
+                f'{nested_url}/api/conversations/{sid}/events', json=data
+            )
+            response.raise_for_status()
+
     async def disconnect_from_session(self, connection_id: str):
         # Not supported - clients should connect directly to the nested server!
         raise ValueError('unsupported_operation')
diff --git a/openhands/server/conversation_manager/standalone_conversation_manager.py b/openhands/server/conversation_manager/standalone_conversation_manager.py
@@ -331,13 +331,13 @@ async def send_to_event_stream(self, connection_id: str, data: dict):
         sid = self._local_connection_id_to_session_id.get(connection_id)
         if not sid:
             raise RuntimeError(f'no_connected_session:{connection_id}')
+        await self.send_event_to_conversation(sid, data)
 
+    async def send_event_to_conversation(self, sid: str, data: dict):
         session = self._local_agent_loops_by_sid.get(sid)
-        if session:
-            await session.dispatch(data)
-            return
-
-        raise RuntimeError(f'no_connected_session:{connection_id}:{sid}')
+        if not session:
+            raise RuntimeError(f'no_conversation:{sid}')
+        await session.dispatch(data)
 
     async def disconnect_from_session(self, connection_id: str):
         sid = self._local_connection_id_to_session_id.pop(connection_id, None)
diff --git a/tests/unit/test_cli_settings.py b/tests/unit/test_cli_settings.py
@@ -171,16 +171,17 @@ async def test_modify_llm_settings_basic_success(
         session_instance = MagicMock()
         session_instance.prompt_async = AsyncMock(
             side_effect=[
-                'openai',  # Provider
                 'gpt-4',  # Model
                 'new-api-key',  # API Key
             ]
         )
         mock_session.return_value = session_instance
 
-        # Mock cli_confirm to select the second option (change provider/model) for the first two calls
-        # and then select the first option (save settings) for the last call
-        mock_confirm.side_effect = [1, 1, 0]
+        # Mock cli_confirm to:
+        # 1. Select the first provider (openai) from the list
+        # 2. Select "Select another model" option
+        # 3. Select "Yes, save" option
+        mock_confirm.side_effect = [0, 1, 0]
 
         # Call the function
         await modify_llm_settings_basic(app_config, settings_store)
@@ -189,8 +190,8 @@ async def test_modify_llm_settings_basic_success(
         app_config.set_llm_config.assert_called_once()
         args, kwargs = app_config.set_llm_config.call_args
         # The model name might be different based on the default model in the list
-        # Just check that it starts with 'openai/'
-        assert args[0].model.startswith('openai/')
+        # Just check that it contains 'gpt-4' instead of checking for prefix
+        assert 'gpt-4' in args[0].model
         assert args[0].api_key.get_secret_value() == 'new-api-key'
         assert args[0].base_url is None
 
@@ -199,8 +200,8 @@ async def test_modify_llm_settings_basic_success(
         args, kwargs = settings_store.store.call_args
         settings = args[0]
         # The model name might be different based on the default model in the list
-        # Just check that it starts with openai/
-        assert settings.llm_model.startswith('openai/')
+        # Just check that it contains 'gpt-4' instead of checking for prefix
+        assert 'gpt-4' in settings.llm_model
         assert settings.llm_api_key.get_secret_value() == 'new-api-key'
         assert settings.llm_base_url is None
 
@@ -249,7 +250,7 @@ async def test_modify_llm_settings_basic_user_cancels(
         'openhands.cli.settings.LLMSummarizingCondenserConfig',
         MockLLMSummarizingCondenserConfig,
     )
-    async def test_modify_llm_settings_basic_invalid_input(
+    async def test_modify_llm_settings_basic_invalid_provider_input(
         self,
         mock_print,
         mock_confirm,
@@ -270,8 +271,7 @@ async def test_modify_llm_settings_basic_invalid_input(
             side_effect=[
                 'invalid-provider',  # First invalid provider
                 'openai',  # Valid provider
-                'invalid-model',  # Invalid model
-                'gpt-4',  # Valid model
+                'custom-model',  # Custom model (now allowed with warning)
                 'new-api-key',  # API key
             ]
         )
@@ -284,34 +284,32 @@ async def test_modify_llm_settings_basic_invalid_input(
         # Call the function
         await modify_llm_settings_basic(app_config, settings_store)
 
-        # Verify error messages were shown for invalid inputs
-        assert (
-            mock_print.call_count >= 2
-        )  # At least two error messages should be printed
+        # Verify error message was shown for invalid provider and warning for custom model
+        assert mock_print.call_count >= 2  # At least two messages should be printed
 
-        # Check for invalid provider error
+        # Check for invalid provider error and custom model warning
         provider_error_found = False
-        model_error_found = False
+        model_warning_found = False
 
         for call in mock_print.call_args_list:
             args, _ = call
             if args and isinstance(args[0], HTML):
                 if 'Invalid provider selected' in args[0].value:
                     provider_error_found = True
-                if 'Invalid model selected' in args[0].value:
-                    model_error_found = True
+                if 'Warning:' in args[0].value and 'custom-model' in args[0].value:
+                    model_warning_found = True
 
         assert provider_error_found, 'No error message for invalid provider'
-        assert model_error_found, 'No error message for invalid model'
+        assert model_warning_found, 'No warning message for custom model'
 
-        # Verify LLM config was updated with correct values
+        # Verify LLM config was updated with the custom model
         app_config.set_llm_config.assert_called_once()
 
-        # Verify settings were saved
+        # Verify settings were saved with the custom model
         settings_store.store.assert_called_once()
         args, kwargs = settings_store.store.call_args
         settings = args[0]
-        assert settings.llm_model == 'openai/gpt-4'
+        assert 'custom-model' in settings.llm_model
         assert settings.llm_api_key.get_secret_value() == 'new-api-key'
         assert settings.llm_base_url is None
 

Original file line number	Diff line number	Diff line change
`@@ -104,8 +104,9 @@`
`104`	`104`	`]`
`105`	`105`	`},`
`106`	`106`	`{`
`107`		`- "group": "Customization",`
	`107`	`+ "group": "Customizations & Settings",`
`108`	`108`	`"pages": [`
	`109`	`+ "usage/common-settings",`
`109`	`110`	`"usage/prompting/repository",`
`110`	`111`	`{`
`111`	`112`	`"group": "Microagents",`