We added a dependency between api proposals. Looks like tsgo is more strict about not picking this up automatically so we need to make sure there is an import so the dependency is picked up
* Track external tool calls
* Tools in progress work, subagents do not
* Remove the subagent stuff
* Safer
* Remove this
* Build fix
* Bump proposed API
Because this would lead to showing all tool calls twice in CC
* Remove this
* hooks streaming first pass
* Update src/vs/workbench/contrib/chat/browser/widget/chatContentParts/chatHookContentPart.ts
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* update styling
* modify api shape
* address some comments + do not render for now
* new icons + no more continue
* make sure we render right, some comments addressed
* uncomment that stuffs
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Add usage data to chat result api
* Start prototyping status icon
* Cleanup old context widget
* Cleanup widget
* Grow outwards
* Some cleanups and refacotors
* Make actions contributable
* Add action header
* Cleanup action rendering
* Add sub categories of token usage
* cleanup diff
* Handle copilot feedback
* chat: support representing file deletions in edit sessions
Add support for file deletion operations in chat editing sessions through
new ChatResponseWorkspaceEditPart. This allows agents to represent file-level
operations (deletions, creations, renames) alongside text and notebook edits.
- Adds ChatEditingDeletedFileEntry class to represent deleted files with
proper diff display and restoration functionality
- Introduces ChatResponseWorkspaceEditPart and IChatWorkspaceEdit interfaces
for file-level operations at the workspace level
- Implements workspace edit streaming through chat editing sessions with
proper undo/redo support
- Adds ChatWorkspaceEditContentPart for UI rendering of file operations
- Extends chat session storage to serialize deleted file entries
- Supports both acceptance and rejection of file deletions with proper state
management and snapshotting
Ref https://github.com/microsoft/vscode/issues/275705
(Commit message generated by Copilot)
* fix test
* Support UX for parallel subagents
Similar to thinking ux
* Show prompt when expanded as well
* Add ellipsis
* Fix unit test
* Get subagents working with tool streaming changes
* Fixes
* Just keep this the same, close enough
This is a rethinking of the initial API proposed in `languageModelToolSupportsModel.d.ts`.
1. This switches to `models?: LanguageModelChatSelector[];` to control enablement.
definitely open to switching this out, but I think a synchronously-analyzable
expression is important to retain the data flows in core without too many races.
2. The extension is able to define a tool at runtime via registerToolDefinition. This
should let us have entirely service-driven tools from model providers without
requiring a static definition for each one. We can also have model-specific
variants of tools without a ton of package.json work for each variant of the tool
(as initially proposed using `when` clauses)
This then propagates that down into the tools service. Currently I have this as just
compiling to a `when` expression once it reaches the main thread. Then, for the tools
service, it takes an IContextKeyService in cases where tools should be enumerated,
and the chat input sets the model keys in its scoped context key service. This allows
the tools to be filtered correctly in the tool picker.
I initially thought about allowing multiple definitions be registered for the same tool
name/id for model-specific variants of tools but I realized that gets really gnarly and
we already have a `toolReferenceName` that multiple tools can register into.
Todo for tomorrow morning:
- Tools don't make it to the ChatRequest yet, or something, still need to investigate
- Need to make sure tools in prompts/models all work. For a first pass I think we can
let prompts/modes reference all tools by toolReferenceName.
- Validate that multiple tools actually can safely share a reference name (and do
some priority ordering?)
- General further validation
- Some unit tests
Allows external agent/CLI edits to be harnessed in our edit session
implementation. There is a callback API to make an external edit. While
the callback is running, we assume that all edits made were done by the
agent and update our internal models based on a before/after snapshot.
We want to prevent mistaken changes that do something like this:
```ts
foo.onEvent = () => { ... };
```
When they almost always mean:
```ts
foo.onEvent(() => { ... })
```
* Add the ability to clear a ChatResponseStream, passing in a reason which results in a warning being displayed
* Changing ChatResponseStream.clear to ChatResponseStream.clearToPreviousToolInvocation and only clearing up to the last tool invocation
* Remove unnecessary code block
Co-authored-by: James Wang <120431051+jwangxx@users.noreply.github.com>
