🤖 feat: add self-extension tip to the chat placeholder carousel

[ibetitsmike]

Summary

Adds a rotating chat-input placeholder tip that prompts users to ask Xum to write a skill, author a durable workflow, or investigate an issue in Xum itself. Users are largely unaware that Xum can extend and debug itself; the placeholder carousel is the passive discovery surface for exactly this kind of capability.

Background

The carousel in placeholderTips.ts only advertised slash commands, symbol shortcuts, and keybinds. Nothing surfaced the self-extension story: skills in .xum/skills/, durable workflows via the built-in workflow-authoring skill, or asking Xum to diagnose its own behavior.

Implementation

• New tip at slot 1. The Storybook-pinned lead tip at slot 0 is unchanged, so no visual baselines move.
• workflow_run and workflow_resume are only registered when the Dynamic Workflows experiment is enabled (off by default), and the carousel has a standing rule against advertising flag-locked features. The durable-workflow clause is therefore shown only when the experiment is on: getPlaceholderTips(options) builds the list from the caller's experiment state and ChatInput passes its existing dynamicWorkflowsExperimentEnabled value. Both variants keep identical length and order so the wall-clock rotation stays aligned.
• Default: Ask Xum to write a skill, or to investigate an issue in Xum
• Experiment on: Ask Xum to write a skill or durable workflow, or to investigate an issue in Xum

Validation

• New unit test asserts the gating: the workflow clause is absent by default, present with the flag, and the variant swaps exactly one slot without changing list length.

Risks

Low. Placeholder copy plus a small refactor of the tip list into a builder; rotation math and the Storybook pin are unchanged.

---

Generated with xum • Model: anthropic:claude-fable-5-1 • Thinking: xhigh • Cost: $4.71

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-14T11:52:48.260632Z	5fbeac1	Manual request
🔒 Security Review	✅ Completed 2026-09-14T11:52:33.441225Z	5fbeac1	Manual request

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 review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[ibetitsmike]

@codex review

[chatgpt-codex-connector]

🛡️ Codex Security Review · Automatically triggered

Security review completed. No security issues were found in this pull request.

Reviewed commit: 5fbeac15d2

View security finding report

Only the user who started this review can view the report in Codex.

ℹ️ About Codex security reviews in GitHub

This is an experimental Codex feature. Security reviews are triggered when:

• You comment "@codex security review"
• A regular code review gets triggered (for example, "@codex review" or when a PR is opened), and you’re opted in so security review runs alongside code review

Once complete, Codex will leave suggestions, or a comment if no findings are found.

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. Keep them coming!

Reviewed commit: 5fbeac15d2

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 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 address that feedback".