You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: api/extension-guides/tools.md
+7-7Lines changed: 7 additions & 7 deletions
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ MetaDescription: A guide to creating a language model tool and how to implement
9
9
10
10
# Language Model Tool API
11
11
12
-
Language model tools enable you to extend the functionality of a large language model (LLM). VS Code surfaces tools contributed by extensions in Copilot [agent mode](/docs/copilot/chat/chat-agent-mode.md). By contributing a tool in a VS Code extension, you can combine the power of agentic coding with deep VS Code integration via its extension APIs.
12
+
Language model tools enable you to extend the functionality of a large language model (LLM). VS Code surfaces tools contributed by extensions in Copilot [agent mode](/docs/copilot/chat/chat-agent-mode). By contributing a tool in a VS Code extension, you can combine the power of agentic coding with deep VS Code integration via its extension APIs.
13
13
14
14
In this extension guide, you'll learn how to create a language model tool and how to implement tool calling in a chat extension.
15
15
@@ -27,7 +27,7 @@ By implementing a language model tool in your extension, you can:
27
27
28
28
-**Extend agent mode** with specialized tools that are automatically invoked as part of responding to a user prompt. For example, enable database scaffolding and querying as part of a chat conversation.
29
29
-**Extend ask and edit mode** with specialized tools that users can reference directly in a chat prompt with `#`. For example, to fetch content from the web.
30
-
-**Deeply integrate with VS Code** by using the broad set of extension APIs. For example, use the [debug APIs](/api/extension-guides/debugger-extension.md) to augment a user's debugging experience.
30
+
-**Deeply integrate with VS Code** by using the broad set of extension APIs. For example, use the [debug APIs](/api/extension-guides/debugger-extension) to augment a user's debugging experience.
31
31
32
32
## Create a language model tool
33
33
@@ -51,13 +51,13 @@ The static configuration of the tool is defined in the `package.json` file of yo
51
51
|`name`| The unique name of the tool, used to reference the tool in the extension implementation code. Format the name in the format `{verb}_{noun}`. See [naming guidelines](#guidelines). |
52
52
|`displayName`| The user-friendly name of the tool, used for displaying in the UI. |
53
53
54
-
1. If the tool can be used in [agent mode](/docs/copilot/chat/chat-agent-mode.md) or referenced in a chat prompt with `#`, add the following properties:
54
+
1. If the tool can be used in [agent mode](/docs/copilot/chat/chat-agent-mode) or referenced in a chat prompt with `#`, add the following properties:
55
55
56
56
Users can enable or disable the tool in the Chat view, similar to how this is done for [Model Context Protocol (MCP) tools](/docs/copilot/chat/mcp-servers).
57
57
58
58
| Property | Description |
59
59
| -------- | ----------- |
60
-
|`canBeReferencedInPrompt`| Set to `true` if the tool can be used in [agent mode](/docs/copilot/chat/chat-agent-mode.md) or referenced in chat. |
60
+
|`canBeReferencedInPrompt`| Set to `true` if the tool can be used in [agent mode](/docs/copilot/chat/chat-agent-mode) or referenced in chat. |
61
61
|`toolReferenceName`| The name for users to reference the tool in a chat prompt via `#`. |
62
62
|`icon`| The icon to display for the tool in the UI. |
63
63
|`userDescription`| User-friendly description of the tool, used for displaying in the UI. |
@@ -267,6 +267,6 @@ Get more best practices for creating tools in the [OpenAI documentation](https:/
0 commit comments