anomalyco / anomalyco/opencode

[FEATURE]: Show subagent start time and execution duration

Open
#42,564 3 comments 0 reactions 1 assignee View on GitHub

@simonklee is already working on this.

Since Aug 14, 2026.

Dominant language
TypeScript
Stars
209k
Forks
27.5k
Avg merge
7h 2m
Merged PRs (30d)
384

Description

Description:

It would be very useful to display timing information for subagent calls in the UI.

Currently, when multiple subagents are invoked, it can be difficult to understand when each subagent was started and how long it took to complete, especially when several agents are running or being delegated in sequence.

Proposed enhancement

For each subagent invocation, display:

  • Invocation time — when the subagent was started.
  • Execution duration — how long the subagent took to complete.
  • Optionally, completion time as well, if it fits naturally into the existing UI.

For example, the UI could show something similar to:

▣ Delegators/Workers/Openai-Gpt-5.6-Luna/...    15:02:31
   Completed in 42s

▣ General                                        15:03:14
   Completed in 18s

▣ Code-Reviewers/Openai-Gpt-5.6-Luna/...         15:03:35
   Completed in 1m 07s

This would make it much easier to understand the execution flow, identify slow subagents, and debug or analyze complex multi-agent workflows.

Why this would be useful

This information would help with:

  • understanding the timeline of agent/subagent execution;
  • identifying slow or unexpectedly long-running subagents;
  • debugging delegation and parallel execution;
  • comparing execution times between different agents;
  • getting a clearer picture of overall workflow performance.

The timestamp could be displayed inline with the subagent call, while the duration could be added once the subagent finishes.

Example

Example of the proposed UI

I think even a minimal implementation showing the start time + execution duration would already provide a lot of value.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.