Add @expo/code-review-cli - #58021
Draft
Abbondanzo wants to merge 4 commits into
Draft
Conversation
Scaffolded with `ecr init --token-env META_API_KEY`, model set to `meta/muse-spark-1.2` with auth `meta/api-key/META_API_KEY`. Workflows wired to META_API_KEY and ECR_EXPECTED_TOKEN_ENV, Claude CLI install step removed per Muse-only setup. Verified locally: verify-config OK, doctor 3 agents (consistency/correctness/security) + coordinator, ref-check OK, review correctly gates on META_API_KEY. Integration stops at credential — set META_API_KEY repo secret (Meta AI developer portal) and optional ECR_VERSION/BRAVE_SEARCH_API_KEY to enable.
meta-cla
Bot
added
the
CLA Signed
Abbondanzo
marked this pull request as draft
August 19, 2026 18:32
Abbondanzo
changed the title
- Forward META_API_KEY from secrets.EXPO_CODE_REVIEW_API_KEY as you defined (env var stays META_API_KEY to match tokenEnv) - Add continue-on-error to Guard step so initial PR that introduces .expo-code-review/ does not fail the job when base has no config (expected fail-closed, next PR will be first reviewed) - Mirrored in command workflow
Set review.trigger to label so ecr ci self-gates to PRs labeled ai-review (or ai-review:<agent>), with ai-review:skip still winning. Keeps the workflow's coarse skip-label gate as spin-up avoidance; real policy is now config-driven.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
This adds an AI code review bot to React Native. It leaves a single comment on PRs with findings from three reviewers (correctness, security, consistency) and never blocks merging or auto-approves.
How it works:
.expo-code-review/—config.jsonc, shared prompts, and the three agent files. The model ismeta/muse-spark-1.2(Muse Spark) usingMETA_API_KEY.pull_request, on-demand/reviewcomment, and/dismissto hide a finding. They check out the base commit and run the published@expo/code-review-clivianpx, so PR code is never executed.What changed:
.expo-code-review/with the config and prompts.github/workflows/expo-code-review.yml,expo-code-review-command.yml,expo-code-review-dismiss.ymlThe bot is wired but dormant until the
META_API_KEYsecret is set (from https://developer.meta.com/ai/, stored asEXPO_CODE_REVIEW_API_KEYand forwarded asMETA_API_KEY). It now only runs when you add theai-reviewlabel.Changelog:
[INTERNAL] [ADDED] - Add @expo/code-review-cli AI code review (Muse Spark)
Test Plan:
Tested locally on
add-expo-code-review-muse-spark(Abbondanzo/react-nativefork):CI is
continue-on-errorandpull-requests: writeonly. After the secret is set, addingai-reviewon a PR triggers the review.