microsoft / microsoft/vscode

Show response duration and token usage after each Copilot Chat response

Open
#329,334 0 comments 0 reactions 1 assignee Claimed by @justschen View on GitHub
Dominant language
TypeScript
Stars
193k
Forks
42.4k
PR merge metrics
PR metrics pending

Description

Description

It would be useful to display a small status summary at the end of every Copilot Chat response, showing:

* How long the latest request took to complete
* How many tokens were used for the request
* Optionally, a breakdown between input and output tokens

For example:

Completed in 12.4s · 8,230 tokens
Input: 6,900 · Output: 1,330

Why is this useful?

This information would help users:

* Understand the cost and size of different prompts
* Compare models and agent workflows
* Identify requests that consume a large amount of context
* Measure the performance of tools, skills and MCP servers
* Optimize prompts and reduce unnecessary token usage

This could be shown as subtle metadata below the final response, possibly inside a collapsible section to avoid adding visual noise.

Additional suggestion

For agent mode, it would also be useful to show:

* Total execution time
* Total token usage across all model calls
* Number of model calls
* Time spent running tools

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.