Harden update-system-interface: ground UI fixes in the real motivating scenario#193
Open
gnguralnick wants to merge 4 commits into
Open
Harden update-system-interface: ground UI fixes in the real motivating scenario#193gnguralnick wants to merge 4 commits into
gnguralnick wants to merge 4 commits into
Conversation
…g scenario; close preview tab on teardown A UI fix delegated through this skill validated against a fixture the worker invented rather than the real conversation that motivated the change, producing a CSS selector that never matched the real DOM plus a passing-but-meaningless test. Close the process gaps at the three points where the real scenario should have entered, and fix a teardown gap: - Delegate: the lead must capture the real motivating DOM/measurements and pass them in the brief under a new `## Real scenario to reproduce` section, as the worker's reproduction fixture and acceptance target. - Preview: the preview opens on the worker's own empty agent, not the motivating conversation; the lead must open the real agent, re-measure, and confirm the number actually moved before asking the user. - Worker sub-skill: the fixture must reproduce the lead-provided DOM shape (not a guess), assert that shape, and the regression test must fail-before/pass-after. - Teardown: `unpreview` tears down the preview servers/services but leaves the `si-preview` dockview tab open; add an explicit step to close it (layout panel vs. service lifecycle are separate concerns). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This was referenced Jun 22, 2026
added 3 commits
June 24, 2026 10:47
…tion instead of transcribing the DOM The worker is not cut off from the motivating conversation -- the system interface discovers agents from the shared MNGR_HOST_DIR, so an instance the worker boots renders the same real conversations the user sees. So the lead names the motivating agent and the worker looks at it firsthand, rather than the lead measuring the DOM and the worker reconstructing it from prose.
…stem-interface # Conflicts: # .agents/skills/update-system-interface/SKILL.md # .agents/skills/update-system-interface/assets/worker/SKILL.md
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.
Motivation
A UI fix delegated through the
update-system-interfaceflow failed because the worker — running in an isolated worktree with its own empty agent — could not see the conversation that motivated the change. It invented a fixture (prose folded inside the permission card), so its CSS selector never matched the real DOM (where the prose is a separate trailing reply,.pv-final), and its test passed against the wrong structure. The miss was only caught by rendering the real conversation and measuring it.Changes
Closes the three points where the real scenario should have entered, plus a teardown gap:
SKILL.md): the lead must capture the real motivating DOM/measurements and pass them in the brief under a new## Real scenario to reproducesection, used as the worker's reproduction fixture and acceptance target.SKILL.md): documents that the preview opens on the worker's own empty agent, not the motivating conversation, and requires the lead to open the real agent, re-measure, and confirm the number actually moved before asking the user.assets/worker/SKILL.md): forbids inventing a fixture when a real scenario is given — the fixture must reproduce that exact DOM shape, assert the shape, and the regression test must fail-before/pass-after.SKILL.md):unpreviewtears down the preview servers/services but leaves thesi-previewdockview tab open; added an explicit step to close it (layout panel vs. service lifecycle are separate concerns).Prose-only; no scripts changed.
🤖 Generated with Claude Code