Skip to content

Commit e1bcf96

Browse files
committed
Add todo list
1 parent 34d7f1e commit e1bcf96

File tree

3 files changed

+19
-1
lines changed

3 files changed

+19
-1
lines changed

docs/copilot/reference/copilot-settings.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -69,11 +69,12 @@ The team is continuously working on improving Copilot in VS Code and adding new
6969
| `setting(github.copilot.chat.agent.autoFix)`<br/>Automatically diagnose and fix issues in the generated code changes. | `true` |
7070
| `setting(github.copilot.chat.agent.runTasks)`<br/>Run workspace tasks when using agent mode. | `true` |
7171
| `setting(chat.mcp.enabled)`<br/>Enable Model Context Protocol (MCP) support in VS Code. This enables adding tools from MCP servers in agent mode. | `true` |
72+
| `setting(chat.tools.terminal.autoApprove)` <br/>Control which terminal commands are [auto-approved in agent mode](/docs/copilot/chat/chat-agent-mode.md#autoapprove-terminal-commands-experimental). Commands can be set to `true` (auto-approve) or `false` (require approval). Regular expressions can be used by wrapping patterns in `/` characters. | `{ "rm": false, "rmdir": false, "del": false, "kill": false, "curl": false, "wget": false, "eval": false, "chmod": false, "chown": false, "/^Remove-Item\\b/i": false }` |
7273
| `setting(chat.mcp.autoStart)` _(Experimental)_<br/>Automatically start MCP servers when MCP configuration changes are detected. | `never` |
7374
| `setting(chat.tools.autoApprove)` _(Experimental)_<br/>Automatically approve all tools. | `false` |
75+
| `setting(chat.todoListTool.enabled)` _(Experimental)_<br/>Enable the todo list tool in chat. | `false` |
7476
| `setting(github.copilot.chat.newWorkspaceCreation.enabled)` _(Experimental)_<br/>Enable the agent mode tool for scaffolding a new workspace in chat. | `true` |
7577
| `setting(github.copilot.chat.agent.thinkingTool:true)` _(Experimental)_<br/>Enable the thinking tool in agent mode. | `false` |
76-
| `setting(chat.tools.terminal.autoApprove)` _(Experimental)_<br/>Control which terminal commands are [auto-approved in agent mode](/docs/copilot/chat/chat-agent-mode.md#autoapprove-terminal-commands-experimental). Commands can be set to `true` (auto-approve) or `false` (require approval). Regular expressions can be used by wrapping patterns in `/` characters. | `{ "rm": false, "rmdir": false, "del": false, "kill": false, "curl": false, "wget": false, "eval": false, "chmod": false, "chown": false, "/^Remove-Item\\b/i": false }` |
7778
| `setting(github.copilot.chat.virtualTools.threshold)` _(Experimental)_<br/>Tool count over which virtual tools should be used. Virtual tools group similar sets of tools together and enable the model to activate them on-demand. Enables you to go beyond the limit of 128 tools for a chat request. | `128` |
7879

7980
## Inline chat settings
Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
version https://git-lfs.github.com/spec/v1
2+
oid sha256:48dbae531314d36a467d69df505cc8370436705ce6aca4ff94aaa208dab9e83d
3+
size 872634

release-notes/v1_103.md

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -134,6 +134,20 @@ Early terminal auto-approve settings were introduced last month. This release, t
134134
- The auto approve reasoning is now logged to the Terminal Output channel. We plan to [surface this in the UI soon](https://github.com/microsoft/vscode/issues/256780).
135135
- For now auto approve will only be allowed in either User or Remote settings. We do plan to allow their use in workspace settings again in an upcoming release.
136136
137+
### Track progress with task lists (Experimental)
138+
139+
**Setting**: `setting(chat.todoListTool.enabled)`
140+
141+
The great thing about agent mode is that you can give it a high level task and have it implement it. As it plans the work and breaks it down into smaller tasks, it can be overwhelming to track the progress of all these individual tasks.
142+
143+
This milestone, we are introducing the task/todo list feature in chat to better help you see which tasks are completed and which ones are still pending. You can view the task list at the top of the Chat view, so you always have visibility into the progress being made. As the agent progresses through its work, it updates the task list.
144+
145+
Get started by giving the agent a high-level task and ask it to track its work in a todo list!
146+
147+
<video src="images/1_103/chat-todo-list.mp4" title="Video that shows the todo list in chat." autoplay loop controls muted></video>
148+
149+
This feature is still experimental and you can enable it with the `setting(chat.todoListTool.enabled)` setting.
150+
137151
### Improved model management experience
138152
139153
This iteration, we've revamped the chat provider API, which is responsible for language model access. Users are now able to select which models appear in their model picker, creating a more personalized and focused experience.

0 commit comments

Comments
 (0)