Add experimental agent feedback instructions - #98582
Draft
aurorascharff wants to merge 6 commits into
Draft
Conversation
Contributor
Tests PassedCommit: b75f3ce |
aurorascharff
marked this pull request as ready for review
September 11, 2026 19:06
aurorascharff
marked this pull request as draft
September 11, 2026 21:22
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What?
Adds an opt-in
experimental.agentFeedbackflag. When enabled,next devwrites a separate managed block into the project agent-instructions file for detected AI agents.The block preserves the existing feedback threshold, remote gate, base64url handoff, and user-controlled browser review flow, while asking the agent for one structured, de-identified observation. Disabling the flag removes only that managed feedback block.
Why?
This lets us test a clearer feedback-review experience without changing the default agent setup or coupling it to
agentRules.The receiver and review UI are implemented by https://github.com/vercel/front/pull/85739 and must land with this change.
How?
experimental.agentFeedbackthrough config with a default offalseagentRulesVerification
pnpm --filter=next buildNEXT_SKIP_ISOLATE=1 pnpm test-dev-turbo test/development/app-dir/agent-rules-auto-generate/agent-rules-auto-generate.test.ts(13 tests passed)pnpm build-allwas attempted but could not complete on this host because its stable Rust toolchain rejects the SWC bootstrap's nightly-only-Zflags.