feat: Set up comprehensive Python testing infrastructure with Poetry

.gitignore

@@ -107,7 +107,7 @@ ipython_config.py
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
+# NOTE: We DO NOT ignore poetry.lock - it should be committed
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
@@ -160,4 +160,45 @@ dmypy.json
 .pytype/
 
 # Cython debug symbols
-cython_debug/
+cython_debug/
+
+# Claude settings
+.claude/*
+
+# Testing artifacts
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+coverage.xml
+*.cover
+*.py,cover
+pytest_cache/
+.tox/
+.nox/
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+.python-version
+
+# Build artifacts
+build/
+dist/
+*.egg-info/
+*.egg
+.eggs/
+wheels/
+*.whl
+
+# IDE files
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+.project
+.pydevproject
+.settings/

pyproject.toml

@@ -0,0 +1,134 @@
+[tool.poetry]
+name = "cogagent"
+version = "0.1.0"
+description = "CogAgent: A Visual Language Model for GUI Agents"
+authors = ["CogAgent Team"]
+readme = "README.md"
+packages = [{include = "app"}, {include = "inference"}, {include = "finetune"}]
+
+[tool.poetry.dependencies]
+python = "^3.10"
+transformers = ">=4.47.0"
+torch = ">=2.5.1"
+torchvision = ">=0.20.0"
+huggingface-hub = ">=0.25.1"
+sentencepiece = ">=0.2.0"
+jinja2 = ">=3.1.4"
+pydantic = ">=2.9.2"
+timm = ">=1.0.9"
+tiktoken = ">=0.8.0"
+numpy = "1.26.4"
+accelerate = ">=1.1.1"
+sentence-transformers = ">=3.1.1"
+gradio = ">=5.23.2"
+openai = ">=1.70.0"
+einops = ">=0.8.0"
+pillow = ">=10.4.0"
+sse-starlette = ">=2.1.3"
+bitsandbytes = ">=0.43.2"
+spaces = ">=0.31.1"
+pyautogui = ">=0.9.54"
+pyperclip = ">=1.9.0"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.0"
+
+[tool.poetry.group.finetune]
+optional = true
+
+[tool.poetry.group.finetune.dependencies]
+nltk = ">=3.9.1"
+jieba = ">=0.42.1"
+"ruamel.yaml" = ">=0.18.10"
+datasets = "*"
+peft = ">0.15.1"
+rouge-chinese = ">=1.0.3"
+
+[tool.poetry.group.vllm]
+optional = true
+
+[tool.poetry.group.vllm.dependencies]
+vllm = ">=0.6.6"
+
+[tool.poetry.scripts]
+test = "pytest"
+tests = "pytest"
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--strict-config",
+    "--cov=app",
+    "--cov=inference",
+    "--cov=finetune",
+    "--cov-branch",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-fail-under=80",
+    "-v",
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "slow: Slow running tests",
+]
+console_output_style = "progress"
+filterwarnings = [
+    "error",
+    "ignore::UserWarning",
+    "ignore::DeprecationWarning",
+]
+
+[tool.coverage.run]
+source = ["app", "inference", "finetune"]
+branch = true
+parallel = true
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/.venv/*",
+    "*/dist/*",
+    "*/build/*",
+    "*.egg-info/*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "def __str__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING:",
+    "@abstractmethod",
+    "@abc.abstractmethod",
+]
+precision = 2
+show_missing = true
+skip_covered = false
+skip_empty = true
+sort = "Cover"
+
+[tool.coverage.html]
+directory = "htmlcov"
+title = "CogAgent Coverage Report"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

run_validation.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+"""
+Simple validation script to check testing infrastructure setup.
+This can be run without Poetry installation to verify the structure.
+"""
+
+import os
+import sys
+from pathlib import Path
+
+def check_file_exists(filepath, description):
+    """Check if a file exists and print result."""
+    exists = Path(filepath).exists()
+    status = "✓" if exists else "✗"
+    print(f"{status} {description}: {filepath}")
+    return exists
+
+def check_directory_exists(dirpath, description):
+    """Check if a directory exists and print result."""
+    exists = Path(dirpath).exists() and Path(dirpath).is_dir()
+    status = "✓" if exists else "✗"
+    print(f"{status} {description}: {dirpath}")
+    return exists
+
+def check_file_contains(filepath, search_text, description):
+    """Check if a file contains specific text."""
+    try:
+        content = Path(filepath).read_text()
+        contains = search_text in content
+        status = "✓" if contains else "✗"
+        print(f"{status} {description}")
+        return contains
+    except:
+        print(f"✗ {description} (file not readable)")
+        return False
+
+def main():
+    """Run validation checks."""
+    print("Testing Infrastructure Validation")
+    print("=" * 50)
+
+    all_checks_passed = True
+
+    # Check project structure
+    print("\n1. Project Structure:")
+    all_checks_passed &= check_file_exists("pyproject.toml", "Poetry configuration file")
+    all_checks_passed &= check_directory_exists("tests", "Tests directory")
+    all_checks_passed &= check_directory_exists("tests/unit", "Unit tests directory")
+    all_checks_passed &= check_directory_exists("tests/integration", "Integration tests directory")
+    all_checks_passed &= check_file_exists("tests/__init__.py", "Tests package init")
+    all_checks_passed &= check_file_exists("tests/unit/__init__.py", "Unit tests init")
+    all_checks_passed &= check_file_exists("tests/integration/__init__.py", "Integration tests init")
+    all_checks_passed &= check_file_exists("tests/conftest.py", "Pytest configuration")
+    all_checks_passed &= check_file_exists("tests/test_setup_validation.py", "Validation tests")
+
+    # Check pyproject.toml contents
+    print("\n2. Poetry Configuration:")
+    all_checks_passed &= check_file_contains("pyproject.toml", "[tool.poetry]", "Poetry section")
+    all_checks_passed &= check_file_contains("pyproject.toml", "[tool.poetry.dependencies]", "Dependencies section")
+    all_checks_passed &= check_file_contains("pyproject.toml", "[tool.poetry.group.dev.dependencies]", "Dev dependencies")
+    all_checks_passed &= check_file_contains("pyproject.toml", "pytest", "Pytest dependency")
+    all_checks_passed &= check_file_contains("pyproject.toml", "pytest-cov", "Coverage dependency")
+    all_checks_passed &= check_file_contains("pyproject.toml", "pytest-mock", "Mock dependency")
+
+    # Check pytest configuration
+    print("\n3. Pytest Configuration:")
+    all_checks_passed &= check_file_contains("pyproject.toml", "[tool.pytest.ini_options]", "Pytest config section")
+    all_checks_passed &= check_file_contains("pyproject.toml", "[tool.coverage", "Coverage config section")
+    all_checks_passed &= check_file_contains("pyproject.toml", 'test = "pytest"', "Test script command")
+    all_checks_passed &= check_file_contains("pyproject.toml", 'tests = "pytest"', "Tests script command")
+
+    # Check test markers
+    print("\n4. Test Markers:")
+    all_checks_passed &= check_file_contains("pyproject.toml", '"unit: Unit tests"', "Unit test marker")
+    all_checks_passed &= check_file_contains("pyproject.toml", '"integration: Integration tests"', "Integration test marker")
+    all_checks_passed &= check_file_contains("pyproject.toml", '"slow: Slow running tests"', "Slow test marker")
+
+    # Check fixtures
+    print("\n5. Test Fixtures:")
+    all_checks_passed &= check_file_contains("tests/conftest.py", "def temp_dir", "Temp directory fixture")
+    all_checks_passed &= check_file_contains("tests/conftest.py", "def mock_model_config", "Model config fixture")
+    all_checks_passed &= check_file_contains("tests/conftest.py", "def mock_tokenizer", "Tokenizer fixture")
+
+    # Check .gitignore updates
+    print("\n6. Git Configuration:")
+    all_checks_passed &= check_file_contains(".gitignore", ".claude/*", "Claude settings ignored")
+    all_checks_passed &= check_file_contains(".gitignore", "# NOTE: We DO NOT ignore poetry.lock", "Poetry lock note")
+
+    # Summary
+    print("\n" + "=" * 50)
+    if all_checks_passed:
+        print("✓ All validation checks passed!")
+        print("\nNext steps:")
+        print("1. Run: poetry install --with dev")
+        print("2. Run: poetry run test")
+        print("3. Run: poetry run tests")
+        return 0
+    else:
+        print("✗ Some validation checks failed!")
+        return 1
+
+if __name__ == "__main__":
+    sys.exit(main())