diff --git a/.github/workflows/nightly-llm.yaml.disabled b/.github/workflows/nightly-llm.yaml.disabled
new file mode 100644
index 00000000..f29bff0c
--- /dev/null
+++ b/.github/workflows/nightly-llm.yaml.disabled
@@ -0,0 +1,96 @@
+# =============================================================================
+# AWOOOI Nightly LLM Tests (2026-03-26)
+# =============================================================================
+# 🤖 完整 LLM 測試 - 每日執行 (CPU 推理需 ~45 分鐘)
+#
+# 測試內容:
+# - test_model_regression.py: 模型回歸測試 (4 案例)
+# - test_prompt_validation.py: Prompt 品質驗證 (5 案例)
+#
+# 觸發時機:
+# - 每日 00:00 UTC (08:00 台北)
+# - 手動觸發
+
+name: Nightly LLM Tests
+
+on:
+  schedule:
+    - cron: '0 0 * * *'  # 每日 00:00 UTC (08:00 台北)
+  workflow_dispatch:
+    inputs:
+      timeout:
+        description: 'Timeout per test (seconds)'
+        required: false
+        default: '300'
+
+concurrency:
+  group: nightly-llm
+  cancel-in-progress: true
+
+env:
+  PYTHON_VERSION: '3.11'
+  OLLAMA_URL: http://192.168.0.188:11434
+  OLLAMA_MODEL: qwen2.5:7b-instruct
+
+jobs:
+  llm-regression:
+    name: LLM Regression Tests
+    runs-on: [self-hosted, harbor, k8s]
+    timeout-minutes: 60  # 1 小時超時
+    steps:
+      # 2026-03-29 Claude Code: 修復 _diag/pages 檔案衝突
+      - name: "Clean Runner Diagnostics"
+        run: |
+          RUNNER_ROOT=$(dirname "$(dirname "$RUNNER_TEMP")")
+          rm -rf "$RUNNER_ROOT/_diag/pages" 2>/dev/null || true
+          mkdir -p "$RUNNER_ROOT/_diag/pages" 2>/dev/null || true
+
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
+      - name: Check Ollama
+        run: |
+          echo "🔗 檢查 Ollama 服務..."
+          if curl -s --connect-timeout 10 ${{ env.OLLAMA_URL }}/api/tags > /dev/null; then
+            echo "✅ Ollama 可用"
+            curl -s ${{ env.OLLAMA_URL }}/api/tags | python3 -c "import sys,json; [print(f'  - {m[\"name\"]}') for m in json.load(sys.stdin).get('models',[])]"
+          else
+            echo "❌ Ollama 無法連線"
+            exit 1
+          fi
+
+      - name: Model Regression Tests
+        working-directory: apps/api
+        env:
+          PYTHONPATH: ${{ github.workspace }}/apps/api
+        run: |
+          echo "🧪 執行模型回歸測試..."
+          echo "   CPU 模式: 預估 ~15-20 分鐘"
+          uv sync
+          uv run pytest tests/test_model_regression.py -v --tb=short \
+            --timeout=${{ github.event.inputs.timeout || '300' }}
+
+      - name: Prompt Validation Tests
+        working-directory: apps/api
+        env:
+          PYTHONPATH: ${{ github.workspace }}/apps/api
+        run: |
+          echo "📝 執行 Prompt 品質驗證..."
+          echo "   CPU 模式: 預估 ~20-25 分鐘"
+          uv run pytest tests/test_prompt_validation.py -v --tb=short \
+            --timeout=${{ github.event.inputs.timeout || '300' }}
+
+      - name: Summary
+        if: always()
+        run: |
+          echo "📊 Nightly LLM 測試完成"
+          echo "   Ollama: ${{ env.OLLAMA_URL }}"
+          echo "   Model: ${{ env.OLLAMA_MODEL }}"
+          echo "   Mode: CPU (no GPU)"
diff --git a/apps/api/pyproject.toml b/apps/api/pyproject.toml
index 61c32949..d9ac8164 100644
--- a/apps/api/pyproject.toml
+++ b/apps/api/pyproject.toml
@@ -28,6 +28,8 @@ dependencies = [
     "sentry-sdk[fastapi]>=2.0.0",
     # Langfuse (LLMOps - Phase 15.1，Self-Hosted @ 192.168.0.110:3100)
     "langfuse>=2.0.0",
+    # Prometheus (ADR-037 Wave A.5 監控指標)
+    "prometheus-client>=0.20.0",
     # Phase 6.4g: leWOOOgo Brain - 積木化決策引擎
     # NOTE: Local packages 透過 Dockerfile 預先安裝，無需在此列出
     # 請參閱 apps/api/Dockerfile Phase 6.4i 註解