fix(tui): hide system-trigger messages in resume replay - #1990
Merged
Conversation
Goal mode stores its per-turn continuation prompt as a user message with a system_trigger origin. Live rendering never shows these model-facing messages, but resume replay only filtered three specific system_trigger names, so the continuation prompt leaked into the transcript as a user message. Skip all system_trigger user messages during replay, matching the live path and the markdown exporter, and drop the two goal-specific filters this makes redundant.
🦋 Changeset detectedLatest commit: 46e8474 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
commit: |
![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: 46e847425e
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Related Issue
N/A — the problem is explained below.
Problem
When resuming a session that ran in goal mode, the replay leaks goal mode's internal continuation prompt ("Continue working toward the active goal…") into the transcript as a user message. Each goal turn injects this prompt as a user message carrying a
system_triggerorigin; it is model-facing only and the live TUI never renders it. Resume replay, however, only filtered three specificsystem_triggernames (goal_completion,goal_blocked,goal_fork_cleared), so the continuation prompt fell through to the default branch and rendered as a user message.What changed
system_triggerorigin (goal continuation prompts, goal outcome/cancel reminders, stop-hook reasons, etc.). This matches the live render path and the markdown exporter, which already treat these messages as internal.system_triggerfilters made redundant by the general rule.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.