Uh oh!
There was an error while loading. Please reload this page.
feat(chatbot): auto-publish AI-built apps in chat — the self-use magic moment - #1613
Merged
Conversation
…c moment When the runtime enables `features.autoPublishAiBuilds`, a whole-app build (apply_blueprint, which the backend marks `autoPublishable`) is published the moment the agent finishes — the user lands on a populated, running app with no manual Publish click. Incremental edits are NOT auto-published: they omit the flag and stay drafts for explicit review, so a destructive change never goes live silently. Design: backend declares lifecycle intent → chat decides → the status panel is the single source of truth for publish state (the model only describes what it built). The draft card flips to a "Published" badge once promoted, instead of leaving a stale Publish button. - mapMessages: lift `autoPublishable` + `failedCount` from the draft envelope - ChatbotEnhanced: gate auto-publish on `autoPublishable`; dedup by toolCallId (so repeat builds into one workspace package each fire once); per-toolCallId "Published" badge (a later edit into an already-published package still shows Publish); onPublishDrafts reports success so the badge reflects reality - runtime-config: consume `features.autoPublishAiBuilds` - AiChatPage / ConsoleFloatingChatbot: pass the flag, return publish success - tests: 17 cases incl. scope (edit not auto-published) + badge regressions Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The latest updates on your projects. Learn more about Vercel for GitHub. |
Contributor
✅ Console Performance Budget
📦 Bundle Size Report
Size Limits
|
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 freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
What
When the runtime enables
features.autoPublishAiBuilds, a whole-app build (apply_blueprint, which the backend marksautoPublishable) is published the moment the agent finishes — the user lands on a populated, running app with no manual Publish click. Incremental edits are not auto-published: they stay drafts for explicit review, so a destructive change never goes live silently.Pairs with cloud#176 (the backend policy +
autoPublishableflag).Design
Backend declares lifecycle intent → chat decides → the status panel is the single source of truth for publish state (the model only describes what it built). The draft card flips to a "Published" badge once promoted, instead of leaving a stale Publish button.
Changes
autoPublishable+failedCountfrom the draft envelope.autoPublishable; dedup bytoolCallId(repeat builds into one workspace package each fire once); per-toolCallId "Published" badge (a later edit into an already-published package still shows Publish);onPublishDraftsreports success so the badge reflects reality.features.autoPublishAiBuilds.Verification
plugin-chatbot48 tests (17 for auto-publish incl. scope + badge regressions). Typecheck clean.🤖 Generated with Claude Code