[Ready for review] Add contributors page with data collection pipeline

src/app/(home)/contributors/contributor-card.tsx

@@ -0,0 +1,37 @@
+import Link from "next/link";
+import {
+  Card,
+  CardHeader,
+  CardTitle,
+  CardDescription,
+} from "@/components/ui/card";
+
+interface ContributorCardProps {
+  name: string;
+  githubHandle: string;
+  role: string;
+}
+
+export function ContributorCard({ name, githubHandle, role }: ContributorCardProps) {
+  const hasName = name && name !== githubHandle;
+
+  return (
+    <Link
+      href={`https://github.com/${githubHandle}`}
+      target="_blank"
+      rel="noopener noreferrer"
+      className="-mr-px -mt-px"
+    >
+      <Card className="shadow-none rounded-none h-full hover:bg-sidebar dark:hover:bg-accent transition-colors">
+        <CardHeader>
+          <CardTitle className="font-code text-lg">
+            {hasName ? name : `@${githubHandle}`}
+          </CardTitle>
+          <CardDescription className="font-code text-xs">
+            {hasName ? `@${githubHandle} · ${role}` : role}
+          </CardDescription>
+        </CardHeader>
+      </Card>
+    </Link>
+  );
+}

src/app/(home)/contributors/layout.tsx

@@ -0,0 +1,11 @@
+export default function ContributorsLayout({
+  children,
+}: {
+  children: React.ReactNode;
+}) {
+  return (
+    <main className="flex flex-1 flex-col max-w-7xl w-full mx-auto px-4 pb-4 pt-6 sm:pt-12">
+      <div className="space-y-6">{children}</div>
+    </main>
+  );
+}

src/app/(home)/contributors/page.tsx

@@ -0,0 +1,129 @@
+import contributionData from "../../../../utils/contributors/data/harbor_contribution.json";
+import { ContributorCard } from "./contributor-card";
+import Link from "next/link";
+
+interface Contributor {
+  github_handle: string;
+  email: string;
+  name: string;
+  affiliation: string;
+  role: string;
+  rank: number;
+  adapter_rank: number;
+  pr_count: number;
+  adapter_pr_count: number;
+  non_adapter_pr_count: number;
+  total_additions: number;
+  total_deletions: number;
+  pr_list: { pr_url: string; pr_title: string; pr_type: string }[];
+}
+
+function lastName(c: Contributor): string {
+  const parts = c.name.trim().split(/\s+/);
+  return (parts[parts.length - 1] ?? c.github_handle).toLowerCase();
+}
+
+function partitionContributors(data: Contributor[]) {
+  const harborContributors: Contributor[] = [];
+  const adapterContributors: Contributor[] = [];
+
+  for (const c of data) {
+    if (c.non_adapter_pr_count > 0 || c.rank !== 0) {
+      harborContributors.push(c);
+    }
+    if (c.adapter_pr_count > 0 || c.adapter_rank !== 0) {
+      adapterContributors.push(c);
+    }
+  }
+
+  // Rank first takes priority (descending), then PR count, then last name
+  harborContributors.sort(
+    (a, b) => b.rank - a.rank || b.non_adapter_pr_count - a.non_adapter_pr_count || lastName(a).localeCompare(lastName(b)),
+  );
+  adapterContributors.sort(
+    (a, b) => b.adapter_rank - a.adapter_rank || b.adapter_pr_count - a.adapter_pr_count || lastName(a).localeCompare(lastName(b)),
+  );
+
+  return { harborContributors, adapterContributors };
+}
+
+export default function ContributorsPage() {
+  const data = contributionData as Contributor[];
+  const { harborContributors, adapterContributors } =
+    partitionContributors(data);
+
+  return (
+    <>
+      <div className="space-y-2">
+        <h1 className="text-4xl tracking-tighter font-code font-medium">
+          Contributors
+        </h1>
+        <p className="text-muted-foreground">
+          Harbor is built by an open community of contributors. Interested in
+          contributing?{" "}
+          <Link href="/docs/contributing" className="underline">
+            Learn how to get started
+          </Link>
+          .
+        </p>
+      </div>
+
+      <section className="space-y-4">
+        <h2 className="text-2xl tracking-tighter font-code font-medium">
+          Harbor Contributors
+        </h2>
+        <div className="border rounded-xl overflow-hidden">
+          <div className="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 -m-px bg-card">
+            {harborContributors.map((c) => (
+              <ContributorCard
+                key={`harbor-${c.github_handle}`}
+                name={c.name}
+                githubHandle={c.github_handle}
+                role={c.role}
+              />
+            ))}
+          </div>
+        </div>
+      </section>
+
+      <section className="space-y-4">
+        <h2 className="text-2xl tracking-tighter font-code font-medium">
+          Harbor Adapter Contributors
+        </h2>
+        <div className="border rounded-xl overflow-hidden">
+          <div className="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 -m-px bg-card">
+            {adapterContributors.map((c) => (
+              <ContributorCard
+                key={`adapter-${c.github_handle}`}
+                name={c.name}
+                githubHandle={c.github_handle}
+                role={c.role}
+              />
+            ))}
+          </div>
+        </div>
+      </section>
+
+      <section className="space-y-4">
+        <h2 className="text-2xl tracking-tighter font-code font-medium">
+          Acknowledgments
+        </h2>
+        <div className="border rounded-xl p-6 bg-card">
+          <p className="text-muted-foreground">
+            API inference compute for parity experiments is generously supported
+            by{" "}
+            <Link
+              href="https://www.2077ai.com/"
+              target="_blank"
+              rel="noopener noreferrer"
+              className="underline"
+            >
+              2077AI
+            </Link>
+            .
+          </p>
+        </div>
+      </section>
+    </>
+  );
+}

src/lib/layout.shared.tsx

@@ -21,6 +21,11 @@ export function baseOptions(): BaseLayoutProps {
         text: "Registry",
         active: "nested-url",
       },
+      {
+        url: "/contributors",
+        text: "Contributors",
+        active: "nested-url",
+      },
       {
         url: "https://discord.gg/6xWPKhGDbA",
         text: "Discord",

utils/contributors/README.md

@@ -0,0 +1,112 @@
+# Contributors Data Pipeline
+
+Scripts to collect and aggregate contributor data from the [laude-institute/harbor](https://github.com/laude-institute/harbor) repository. The output is consumed by the `/contributors` page.
+
+## Prerequisites
+
+- Python 3.10+
+- [GitHub CLI (`gh`)](https://cli.github.com/) authenticated with access to the harbor repo (only needed for `refresh`, `refresh-prdata`, `refresh-userdata`)
+
+## Usage
+
+Use `ctbcli` to run the pipeline:
+
+```bash
+# Full refresh: collect PR data + user data from GitHub, then regenerate
+./utils/contributors/ctbcli refresh
+
+# PR data only: re-collect PR data from GitHub and regenerate
+./utils/contributors/ctbcli refresh-prdata
+
+# User data only: re-collect user profiles from GitHub and regenerate
+./utils/contributors/ctbcli refresh-userdata
+
+# Regenerate from existing data (no API calls — use after editing verified data)
+./utils/contributors/ctbcli generate
+```
+
+## Directory Structure
+
+```
+utils/contributors/
+├── ctbcli                  # CLI entrypoint
+├── README.md
+├── src/                    # Python scripts
+│   ├── collect_pr_data.py
+│   ├── collect_user_data.py
+│   └── generate_contributions.py
+└── data/                   # Data files
+    ├── verified_github_users_data.json   # Manually curated (source of truth)
+    ├── raw_pr_data.json                  # Auto-generated from GitHub API
+    ├── raw_github_users_data.json        # Auto-generated from GitHub API
+    └── harbor_contribution.json          # Final output for the web page
+```
+
+## How It Works
+
+### Data flow
+
+```
+GitHub API ──► raw_pr_data.json ──────────────────────┐
+GitHub API ──► raw_github_users_data.json ──┐          │
+                                            ▼          ▼
+              verified_github_users_data.json ──► generate_contributions.py
+                                                       │
+                                                       ▼
+                                              harbor_contribution.json
+                                                       │
+                                                       ▼
+                                              /contributors page
+```
+
+### Scripts (`src/`)
+
+| Script | What it does | API calls |
+|--------|-------------|-----------|
+| `collect_pr_data.py` | Fetches all merged PRs from `laude-institute/harbor`, classifies each by type (`adapter`, `task`, `engineering`, `other`), and writes `raw_pr_data.json` | Yes (slowest) |
+| `collect_user_data.py` | Reads unique author handles from `raw_pr_data.json`, fetches GitHub profiles, and writes `raw_github_users_data.json` | Yes |
+| `generate_contributions.py` | Merges PR data with user data, ranks contributors, and writes `harbor_contribution.json` | No |
+
+### Data files (`data/`)
+
+| File | Source | Editable? | Description |
+|------|--------|-----------|-------------|
+| `verified_github_users_data.json` | Manual | **Yes** | Curated contributor info with verified names, affiliations, roles, and ranks. Takes precedence over raw GitHub data when a handle matches. |
+| `raw_pr_data.json` | `collect_pr_data.py` | No | All merged PRs with author, additions/deletions, title, and type classification |
+| `raw_github_users_data.json` | `collect_user_data.py` | No | GitHub profile data (name, email, company) for each PR author. Used as fallback when a handle is not in the verified data. |
+| `harbor_contribution.json` | `generate_contributions.py` | No | Final aggregated output consumed by the `/contributors` page |
+
+### Verified user data fields
+
+The `verified_github_users_data.json` file supports these fields:
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `github_handle` | Yes | GitHub username |
+| `name` | Yes | Display name |
+| `affiliation` | Yes | Organization or university |
+| `email` | Yes | Contact email |
+| `role` | No | Displayed on card (e.g. `"Co-lead"`, `"Adapter Lead"`, `"Advisor"`). Defaults to `"Contributor"` |
+| `rank` | No | Sort priority for Harbor Contributors section (higher = listed first). Defaults to `0` |
+| `adapter_rank` | No | Sort priority for Adapter Contributors section (higher = listed first). Defaults to `0` |
+
+### Ranking logic
+
+- **Harbor Contributors**: sorted by `rank` (desc) → non-adapter PR count (desc) → last name (asc)
+- **Adapter Contributors**: sorted by `adapter_rank` (desc) → adapter PR count (desc) → last name (asc)
+
+## Common Tasks
+
+**New PRs merged — update the page:**
+```bash
+./utils/contributors/ctbcli refresh
+```
+
+**Edited verified user data (name, role, rank, etc.):**
+```bash
+./utils/contributors/ctbcli generate
+```
+
+**New contributor needs verified info:**
+1. Add an entry to `data/verified_github_users_data.json`
+2. Run `./utils/contributors/ctbcli generate`

utils/contributors/ctbcli

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PYTHON="${PYTHON:-python3}"
+
+run_collect_pr_data() {
+    echo "==> Collecting PR data..."
+    "$PYTHON" "$SCRIPT_DIR/src/collect_pr_data.py"
+}
+
+run_collect_user_data() {
+    echo "==> Collecting user data..."
+    "$PYTHON" "$SCRIPT_DIR/src/collect_user_data.py"
+}
+
+run_generate() {
+    echo "==> Generating contributions..."
+    "$PYTHON" "$SCRIPT_DIR/src/generate_contributions.py"
+}
+
+usage() {
+    cat <<EOF
+Usage: $0 <command>
+
+Commands:
+  refresh             Collect PR data, user data, and regenerate contributions
+  refresh-prdata      Collect PR data and regenerate contributions
+  refresh-userdata    Collect user data and regenerate contributions
+  generate            Regenerate contributions from existing data (no API calls)
+EOF
+}
+
+case "${1:-}" in
+    refresh)
+        run_collect_pr_data
+        run_collect_user_data
+        run_generate
+        ;;
+    refresh-prdata)
+        run_collect_pr_data
+        run_generate
+        ;;
+    refresh-userdata)
+        run_collect_user_data
+        run_generate
+        ;;
+    generate)
+        run_generate
+        ;;
+    *)
+        usage
+        exit 1
+        ;;
+esac