Wait for agent loop to finish in automation #262370
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
connor4312
previously approved these changes
Aug 19, 2025
connor4312
reviewed
Aug 19, 2025
extensions/vscode-api-tests/src/singlefolder-tests/chat.test.ts
Outdated
Show resolved
Hide resolved
Co-authored-by: Connor Peet <connor@peet.io>
This reverts commit d8d16db.
rwoll
commented
Aug 19, 2025
mjbvz
previously approved these changes
Aug 19, 2025
Member
Author
|
converting to draft while I debug the CI flake. |
karthiknadig
approved these changes
Aug 20, 2025
connor4312
approved these changes
Aug 20, 2025
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Automation needs to determine when the "chat loop" has reached a terminal state so it can inspect the state of the workspace. To support this,
workbench.action.chat.opennow accepts an optionalblockOnResponseflag (defaulting to non-blocking).Additionally, when a terminal state is reached, automation must be able to determine the precise error that's hit. To support this,
IChatResponseErrorDetails.codehas been added. WhileIChatResponseErrorDetailshas a number of flags (isQuotaExceeded, etc.) we do not want to formally introduce more arbitrary states to the API as flags. Instead,codecan be used/set by a Chat Extension.As a follow up,
getErrorDetailsFromChatFetchErrorin the Chat extension will be updated to set the newcodefield.Co-authored-by: Connor Peet connor@peet.io