Test llm validation trigger

.github/workflows/llm-metadata-validation.yml

@@ -0,0 +1,111 @@
+name: LLM Metadata Validation
+
+on:
+  pull_request:
+    paths:
+      - "data/**"
+      - "scripts/validate_llm_metadata.py"
+      - "tests/test_validate_llm_metadata.py"
+      - ".github/workflows/llm-metadata-validation.yml"
+  workflow_dispatch:
+
+jobs:
+  validate-llm-metadata:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    env:
+      GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: pip
+
+      - name: Install dependencies
+        run: pip install -r requirements.txt
+
+      - name: Detect newly added entry IDs
+        id: changed-ids
+        if: github.event_name == 'pull_request'
+        run: |
+          BASE_SHA="${{ github.event.pull_request.base.sha }}"
+          HEAD_SHA="${{ github.event.pull_request.head.sha }}"
+          ADDED_IDS="$(git diff --unified=0 "${BASE_SHA}" "${HEAD_SHA}" -- data/models.yaml data/datasets.yaml data/tools.yaml \
+            | grep -oE '^\+\s*-?\s*id:.*' \
+            | sed -E 's/^\+\s*-?\s*id:\s*//' \
+            | tr -d '"' \
+            | tr '\n' ',' \
+            | sed 's/,$//')"
+          echo "entry_ids=${ADDED_IDS}" >> "$GITHUB_OUTPUT"
+
+      - name: Skip when no new metadata entries
+        if: github.event_name == 'pull_request' && steps.changed-ids.outputs.entry_ids == ''
+        run: |
+          mkdir -p reports
+          cat <<EOF > reports/llm_validation_report.json
+          {"status":"skipped","skipped_reason":"No newly added metadata entries in this PR.","counts":{"pass":0,"warning":0,"fail":0},"results":[]}
+          EOF
+          cat <<EOF > reports/llm_validation_summary.md
+          # LLM Metadata Validation
+          - Status: \`skipped\`
+          - Pass: \`0\`
+          - Warning: \`0\`
+          - Fail: \`0\`
+          - Skipped reason: No newly added metadata entries in this PR.
+          EOF
+
+      - name: Run LLM metadata validation
+        if: github.event_name != 'pull_request' || steps.changed-ids.outputs.entry_ids != ''
+        run: >
+          python scripts/validate_llm_metadata.py
+          --entry-ids "${{ steps.changed-ids.outputs.entry_ids }}"
+          --output reports/llm_validation_report.json
+          --summary-output reports/llm_validation_summary.md
+
+      - name: Comment validation result on PR
+        if: github.event_name == 'pull_request' && always()
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const fs = require("fs");
+            const marker = "<!-- llm-metadata-validation-comment -->";
+            const summary = fs.readFileSync("reports/llm_validation_summary.md", "utf8");
+            const body = `${marker}\n${summary}`;
+
+            const { owner, repo } = context.repo;
+            const issue_number = context.issue.number;
+
+            const comments = await github.paginate(
+              github.rest.issues.listComments,
+              { owner, repo, issue_number, per_page: 100 }
+            );
+
+            const existing = comments.find((comment) =>
+              comment.user?.type === "Bot" && comment.body?.includes(marker)
+            );
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                owner,
+                repo,
+                comment_id: existing.id,
+                body
+              });
+              core.info(`Updated validation comment: ${existing.id}`);
+            } else {
+              const created = await github.rest.issues.createComment({
+                owner,
+                repo,
+                issue_number,
+                body
+              });
+              core.info(`Created validation comment: ${created.data.id}`);
+            }
+

.gitignore

@@ -19,3 +19,4 @@ env/
 
 # Generated (docs/data.js is a build artifact from generate_site.py)
 docs/data.js
+reports/

data/models.yaml

@@ -416,3 +416,10 @@
     last_updated: '2026-06-14'
   added_date: '2026-05-17'
   tags: []
+- id: test-entry-pi0
+  name: pi0
+  description_en: A robot policy for whole-body humanoid control.
+  description_ko: 휴머노이드 전신 제어를 위한 로봇 정책입니다.
+  tags: [manipulation, pytorch]
+  github_url: https://github.com/Physical-Intelligence/openpi
+  paper_url: https://arxiv.org/abs/2410.24164