Adam Moussa
46cd856fb3
A single-user local dashboard that pulls open PRs from the Sea-Haven-Industries org, reviews each with a Fireworks model in the BLOCK/FIX/NIT/QUESTION format, and posts the review to GitHub as the token owner. Runs only on localhost; secrets stay in a gitignored .env and never reach the browser. Structured as an app/ package plus a static/ frontend so the module imports and static mount resolve. HTTP uses httpx2 (the runtime lib starlette's TestClient now prefers), pinned in requirements.txt. Includes a stdlib-only pytest suite (network mocked, no extra test deps so CI needs only pytest) with a skip-by-default live Fireworks test, and CI wired to the org ci-python-app reusable workflow to lint app and tests and run the mocked suite fully offline. Dependabot covers pip and github-actions. |
||
|---|---|---|
| .github | ||
| app | ||
| static | ||
| tests | ||
| .env.example | ||
| .gitignore | ||
| pyproject.toml | ||
| README.md | ||
| requirements-dev.txt | ||
| requirements.txt | ||
| run.sh | ||
pr-reviewer
A local dashboard that pulls open PRs from your GitHub org, reviews each one with a Fireworks model using the BLOCK / FIX / NIT / QUESTION skill format, and lets you request revisions or post the review to GitHub as yourself.
Everything runs on your machine. This is a local, single-user tool. It is not deployed anywhere, so there is no AWS stack, no CI deploy path, and secrets live only in a local .env (gitignored). Your GitHub token and Fireworks key stay in the backend and never reach the browser.
Setup
cp .env.example .env # then fill in FIREWORKS_API_KEY (and GITHUB_TOKEN if not using gh CLI)
./run.sh
Auth
-
GitHub: leave
GITHUB_TOKENblank to use your localgh auth token, or set a token. Reviews are posted as whoever the token belongs to, so use the token for the account you want to appear as the reviewer.A fine-grained personal access token is recommended (least privilege). Set the resource owner to
Sea-Haven-Industriesand grant only these repository permissions:Permission Level Why Pull requests Read and write read PR data and submit the review Contents Read-only fetch the PR diff Metadata Read-only mandatory (auto-added) Give it access to all repositories you review (the search silently skips any it can't see). Fine-grained tokens are single-owner, so this token only covers the
Sea-Haven-Industriesorg, which is all this tool searches; an org owner may need to approve the token before it works. A classic PAT withreposcope also works but is broader than needed. -
Fireworks: set
FIREWORKS_API_KEY. ChangeFIREWORKS_MODELin.envto swap models.
How it works
- Refresh queue runs your filter (
PR_SEARCH_FILTER, default matches your org filter) and lists the PRs. - Run review fetches the PR diff and sends it to Fireworks. The result is parsed into the four categories plus a summary line and a recommended event.
- Request revision re-runs the review with your notes folded in as a trusted instruction, separate from the untrusted diff.
- Post review to GitHub submits it as a PR review. You confirm the event type (COMMENT / APPROVE / REQUEST_CHANGES) and can edit the body first.
The @mention rule
Any PR whose author login is in MENTION_AUTHORS (default openswe) gets an @author mention prepended to the review summary. Add more logins comma-separated.
Notes
- The diff is treated as untrusted input; the model is instructed to ignore any embedded instructions.
- State is in memory and resets on restart. This is a single-user local tool, not a shared service.
- Large diffs are truncated at
MAX_DIFF_BYTESto control token cost.
Layout
app/
config.py settings from .env
github_client.py search PRs, fetch diffs, post reviews
reviewer.py Fireworks call + skill format + markdown rendering
main.py FastAPI endpoints
static/
index.html the dashboard