Repository navigation
Separate human waits from tool time and cap dangling spans - #204
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a3ea0bf524
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "Codex (@codex) review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "Codex (@codex) address that feedback".
1b49a71 to
930cff2
Compare
930cff2 to
6db1ebc
Compare
Abhijeet Prasad (AbhiPrasad)
left a comment
Abhijeet Prasad (AbhiPrasad)
left a comment
There was a problem hiding this comment.
good catch
2 participants
Summary
wait_kind=user_question, keeping human response time out of tool execution time.Context
The debugging packet showed user response intervals folded into Claude tool durations, Codex tool spans lasting many days, and resumed Codex roots with starts far earlier than their observed creation time.
Validation
cargo check --manifest-path bt-daemon/Cargo.tomlpassed. Tests were not run.