Add Excel LLM benchmarking tool with comprehensive run tracking and reporting

- Implemented `ExcelLLMRunRecord` and `ExcelLLMSummary` data classes for structured run data.
- Created backend protocols for MCP and ZCP Excel backends, including asynchronous context management.
- Developed functions for running benchmark cases, managing tool calls, and evaluating results.
- Added support for progress tracking and checkpointing during benchmarking runs.
- Introduced markdown and JSON report generation for summarizing benchmark results.
- Implemented utility functions for tool argument parsing and duplicate tool call evaluation.

Author: jiayuqi7813

.env.example

@@ -0,0 +1,6 @@
+OPENAI_API_KEY=replace-with-your-provider-key
+OPENAI_BASE_URL=https://api.deepseek.com
+OPENAI_MODEL=deepseek-chat
+
+# Optional aliases for provider-specific scripts.
+DEEPSEEK_API_KEY=

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @jiayuqi7813

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,23 @@
+---
+name: Bug report
+about: Report a defect in the SDK, runtime, compatibility layer, or examples
+title: "[Bug] "
+labels: bug
+assignees: ""
+---
+
+## Summary
+
+## Environment
+
+- Python version:
+- Package install mode:
+- Transport:
+
+## Reproduction
+
+## Expected behavior
+
+## Actual behavior
+
+## Logs or artifacts

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,15 @@
+---
+name: Feature request
+about: Propose a protocol, SDK, docs, or benchmark improvement
+title: "[Feature] "
+labels: enhancement
+assignees: ""
+---
+
+## Problem
+
+## Proposed solution
+
+## Compatibility impact
+
+## Additional context

.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/pull_request_template.md

@@ -0,0 +1,10 @@
+## Summary
+
+## Validation
+
+- [ ] `python -m ruff check src tests examples tools`
+- [ ] `PYTEST_DISABLE_PLUGIN_AUTOLOAD=1 python -m pytest -q`
+
+## Compatibility Notes
+
+## Benchmark / Docs Impact

.github/workflows/benchmark-smoke.yml

@@ -0,0 +1,22 @@
+name: benchmark-smoke
+
+on:
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  smoke:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev,openai,mcp]"
+      - name: Benchmark regression tests
+        env:
+          PYTEST_DISABLE_PLUGIN_AUTOLOAD: "1"
+        run: python -m pytest -q tests/test_benchmark_harness.py tests/test_excel_llm_benchmark.py

.github/workflows/ci.yml

@@ -0,0 +1,31 @@
+name: sdk-ci
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+      - "codex/**"
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev,openai,mcp]"
+      - name: Ruff
+        run: python -m ruff check src tests examples tools
+      - name: Pytest
+        env:
+          PYTEST_DISABLE_PLUGIN_AUTOLOAD: "1"
+        run: python -m pytest -q

.github/workflows/secret-scan.yml

@@ -0,0 +1,17 @@
+name: secret-scan
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+      - "codex/**"
+
+jobs:
+  gitleaks:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: gitleaks/gitleaks-action@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -6,6 +6,9 @@
 
 __pycache__/
 *.py[cod]
+*.egg-info/
 
 node_modules/
 .next/
+benchmark_reports/checkpoints/
+benchmark_reports/**/checkpoints/