test(contract-validator): add comprehensive tests (#193)

Add 34 tests across 3 test modules:
- test_parse_tools.py: 11 tests for README/CLAUDE.md parsing
- test_validation_tools.py: 11 tests for compatibility and agent validation
- test_report_tools.py: 12 tests for report generation and filtering

Coverage: parse_tools 79%, validation_tools 96%, report_tools 89%

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

mcp-servers/contract-validator/tests/__init__.py

@@ -0,0 +1 @@
+# Tests for contract-validator MCP server

mcp-servers/contract-validator/tests/test_parse_tools.py

@@ -0,0 +1,193 @@
+"""
+Unit tests for parse tools.
+"""
+import pytest
+from pathlib import Path
+
+
+@pytest.fixture
+def parse_tools():
+    """Create ParseTools instance"""
+    from mcp_server.parse_tools import ParseTools
+    return ParseTools()
+
+
+@pytest.fixture
+def sample_readme(tmp_path):
+    """Create a sample README.md for testing"""
+    readme = tmp_path / "README.md"
+    readme.write_text("""# Test Plugin
+
+A test plugin for validation.
+
+## Features
+
+- **Feature One**: Does something
+- **Feature Two**: Does something else
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/test-cmd` | Test command |
+| `/another-cmd` | Another test command |
+
+## Agents
+
+| Agent | Description |
+|-------|-------------|
+| `test-agent` | A test agent |
+
+## Tools Summary
+
+### Category A (3 tools)
+`tool_a`, `tool_b`, `tool_c`
+
+### Category B (2 tools)
+`tool_d`, `tool_e`
+""")
+    return str(tmp_path)
+
+
+@pytest.fixture
+def sample_claude_md(tmp_path):
+    """Create a sample CLAUDE.md for testing"""
+    claude_md = tmp_path / "CLAUDE.md"
+    claude_md.write_text("""# CLAUDE.md
+
+## Project Overview
+
+### Four-Agent Model (test)
+
+| Agent | Personality | Responsibilities |
+|-------|-------------|------------------|
+| **Planner** | Thoughtful | Planning via `create_issue`, `search_lessons` |
+| **Executor** | Focused | Implementation via `write`, `edit` |
+
+## Workflow
+
+1. Planner creates issues
+2. Executor implements code
+""")
+    return str(claude_md)
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_basic(parse_tools, sample_readme):
+    """Test basic plugin interface parsing"""
+    result = await parse_tools.parse_plugin_interface(sample_readme)
+
+    assert "error" not in result
+    # Plugin name extraction strips "Plugin" suffix
+    assert result["plugin_name"] == "Test"
+    assert "A test plugin" in result["description"]
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_commands(parse_tools, sample_readme):
+    """Test command extraction from README"""
+    result = await parse_tools.parse_plugin_interface(sample_readme)
+
+    commands = result["commands"]
+    assert len(commands) == 2
+    assert commands[0]["name"] == "/test-cmd"
+    assert commands[1]["name"] == "/another-cmd"
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_agents(parse_tools, sample_readme):
+    """Test agent extraction from README"""
+    result = await parse_tools.parse_plugin_interface(sample_readme)
+
+    agents = result["agents"]
+    assert len(agents) == 1
+    assert agents[0]["name"] == "test-agent"
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_tools(parse_tools, sample_readme):
+    """Test tool extraction from README"""
+    result = await parse_tools.parse_plugin_interface(sample_readme)
+
+    tools = result["tools"]
+    tool_names = [t["name"] for t in tools]
+    assert "tool_a" in tool_names
+    assert "tool_b" in tool_names
+    assert "tool_e" in tool_names
+    assert len(tools) >= 5
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_categories(parse_tools, sample_readme):
+    """Test tool category extraction"""
+    result = await parse_tools.parse_plugin_interface(sample_readme)
+
+    categories = result["tool_categories"]
+    assert "Category A" in categories
+    assert "Category B" in categories
+    assert "tool_a" in categories["Category A"]
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_features(parse_tools, sample_readme):
+    """Test feature extraction"""
+    result = await parse_tools.parse_plugin_interface(sample_readme)
+
+    features = result["features"]
+    assert "Feature One" in features
+    assert "Feature Two" in features
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_interface_not_found(parse_tools, tmp_path):
+    """Test error when README not found"""
+    result = await parse_tools.parse_plugin_interface(str(tmp_path / "nonexistent"))
+
+    assert "error" in result
+    assert "not found" in result["error"].lower()
+
+
+@pytest.mark.asyncio
+async def test_parse_claude_md_agents(parse_tools, sample_claude_md):
+    """Test agent extraction from CLAUDE.md"""
+    result = await parse_tools.parse_claude_md_agents(sample_claude_md)
+
+    assert "error" not in result
+    assert result["agent_count"] == 2
+
+    agents = result["agents"]
+    agent_names = [a["name"] for a in agents]
+    assert "Planner" in agent_names
+    assert "Executor" in agent_names
+
+
+@pytest.mark.asyncio
+async def test_parse_claude_md_tool_refs(parse_tools, sample_claude_md):
+    """Test tool reference extraction from agents"""
+    result = await parse_tools.parse_claude_md_agents(sample_claude_md)
+
+    agents = {a["name"]: a for a in result["agents"]}
+    planner = agents["Planner"]
+
+    assert "create_issue" in planner["tool_refs"]
+    assert "search_lessons" in planner["tool_refs"]
+
+
+@pytest.mark.asyncio
+async def test_parse_claude_md_not_found(parse_tools, tmp_path):
+    """Test error when CLAUDE.md not found"""
+    result = await parse_tools.parse_claude_md_agents(str(tmp_path / "CLAUDE.md"))
+
+    assert "error" in result
+    assert "not found" in result["error"].lower()
+
+
+@pytest.mark.asyncio
+async def test_parse_plugin_with_direct_file(parse_tools, sample_readme):
+    """Test parsing with direct file path instead of directory"""
+    readme_path = Path(sample_readme) / "README.md"
+    result = await parse_tools.parse_plugin_interface(str(readme_path))
+
+    assert "error" not in result
+    # Plugin name extraction strips "Plugin" suffix
+    assert result["plugin_name"] == "Test"

mcp-servers/contract-validator/tests/test_report_tools.py

@@ -0,0 +1,261 @@
+"""
+Unit tests for report tools.
+"""
+import pytest
+from pathlib import Path
+
+
+@pytest.fixture
+def report_tools():
+    """Create ReportTools instance"""
+    from mcp_server.report_tools import ReportTools
+    return ReportTools()
+
+
+@pytest.fixture
+def sample_marketplace(tmp_path):
+    """Create a sample marketplace structure"""
+    import json
+
+    plugins_dir = tmp_path / "plugins"
+    plugins_dir.mkdir()
+
+    # Plugin 1
+    plugin1 = plugins_dir / "plugin-one"
+    plugin1.mkdir()
+    plugin1_meta = plugin1 / ".claude-plugin"
+    plugin1_meta.mkdir()
+    (plugin1_meta / "plugin.json").write_text(json.dumps({"name": "plugin-one"}))
+    (plugin1 / "README.md").write_text("""# plugin-one
+
+First test plugin.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/cmd-one` | Command one |
+
+## Tools Summary
+
+### Tools (2 tools)
+`tool_a`, `tool_b`
+""")
+
+    # Plugin 2
+    plugin2 = plugins_dir / "plugin-two"
+    plugin2.mkdir()
+    plugin2_meta = plugin2 / ".claude-plugin"
+    plugin2_meta.mkdir()
+    (plugin2_meta / "plugin.json").write_text(json.dumps({"name": "plugin-two"}))
+    (plugin2 / "README.md").write_text("""# plugin-two
+
+Second test plugin.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/cmd-two` | Command two |
+
+## Tools Summary
+
+### Tools (2 tools)
+`tool_c`, `tool_d`
+""")
+
+    # Plugin 3 (with conflict)
+    plugin3 = plugins_dir / "plugin-three"
+    plugin3.mkdir()
+    plugin3_meta = plugin3 / ".claude-plugin"
+    plugin3_meta.mkdir()
+    (plugin3_meta / "plugin.json").write_text(json.dumps({"name": "plugin-three"}))
+    (plugin3 / "README.md").write_text("""# plugin-three
+
+Third test plugin with conflict.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/cmd-one` | Conflicting command |
+
+## Tools Summary
+
+### Tools (1 tool)
+`tool_e`
+""")
+
+    return str(tmp_path)
+
+
+@pytest.fixture
+def marketplace_no_plugins(tmp_path):
+    """Create marketplace with no plugins"""
+    plugins_dir = tmp_path / "plugins"
+    plugins_dir.mkdir()
+    return str(tmp_path)
+
+
+@pytest.fixture
+def marketplace_no_dir(tmp_path):
+    """Create path without plugins directory"""
+    return str(tmp_path)
+
+
+@pytest.mark.asyncio
+async def test_generate_report_json_format(report_tools, sample_marketplace):
+    """Test JSON format report generation"""
+    result = await report_tools.generate_compatibility_report(
+        sample_marketplace, "json"
+    )
+
+    assert "error" not in result
+    assert "generated_at" in result
+    assert "summary" in result
+    assert "plugins" in result
+    assert result["summary"]["total_plugins"] == 3
+
+
+@pytest.mark.asyncio
+async def test_generate_report_markdown_format(report_tools, sample_marketplace):
+    """Test markdown format report generation"""
+    result = await report_tools.generate_compatibility_report(
+        sample_marketplace, "markdown"
+    )
+
+    assert "error" not in result
+    assert "report" in result
+    assert "# Contract Validation Report" in result["report"]
+    assert "## Summary" in result["report"]
+
+
+@pytest.mark.asyncio
+async def test_generate_report_finds_conflicts(report_tools, sample_marketplace):
+    """Test that report finds command conflicts"""
+    result = await report_tools.generate_compatibility_report(
+        sample_marketplace, "json"
+    )
+
+    assert "error" not in result
+    assert result["summary"]["errors"] > 0
+    assert result["summary"]["total_issues"] > 0
+
+
+@pytest.mark.asyncio
+async def test_generate_report_counts_correctly(report_tools, sample_marketplace):
+    """Test summary counts are correct"""
+    result = await report_tools.generate_compatibility_report(
+        sample_marketplace, "json"
+    )
+
+    summary = result["summary"]
+    assert summary["total_plugins"] == 3
+    assert summary["total_commands"] == 3  # 3 commands total
+    assert summary["total_tools"] == 5  # a, b, c, d, e
+
+
+@pytest.mark.asyncio
+async def test_generate_report_no_plugins(report_tools, marketplace_no_plugins):
+    """Test error when no plugins found"""
+    result = await report_tools.generate_compatibility_report(
+        marketplace_no_plugins, "json"
+    )
+
+    assert "error" in result
+    assert "no plugins" in result["error"].lower()
+
+
+@pytest.mark.asyncio
+async def test_generate_report_no_plugins_dir(report_tools, marketplace_no_dir):
+    """Test error when plugins directory doesn't exist"""
+    result = await report_tools.generate_compatibility_report(
+        marketplace_no_dir, "json"
+    )
+
+    assert "error" in result
+    assert "not found" in result["error"].lower()
+
+
+@pytest.mark.asyncio
+async def test_list_issues_all(report_tools, sample_marketplace):
+    """Test listing all issues"""
+    result = await report_tools.list_issues(sample_marketplace, "all", "all")
+
+    assert "error" not in result
+    assert "issues" in result
+    assert result["total_issues"] > 0
+
+
+@pytest.mark.asyncio
+async def test_list_issues_filter_by_severity(report_tools, sample_marketplace):
+    """Test filtering issues by severity"""
+    all_result = await report_tools.list_issues(sample_marketplace, "all", "all")
+    error_result = await report_tools.list_issues(sample_marketplace, "error", "all")
+
+    # Error count should be less than or equal to all
+    assert error_result["total_issues"] <= all_result["total_issues"]
+
+    # All issues should have error severity
+    for issue in error_result["issues"]:
+        sev = issue.get("severity", "")
+        if hasattr(sev, 'value'):
+            sev = sev.value
+        assert "error" in str(sev).lower()
+
+
+@pytest.mark.asyncio
+async def test_list_issues_filter_by_type(report_tools, sample_marketplace):
+    """Test filtering issues by type"""
+    result = await report_tools.list_issues(
+        sample_marketplace, "all", "interface_mismatch"
+    )
+
+    # All issues should have matching type
+    for issue in result["issues"]:
+        itype = issue.get("issue_type", "")
+        if hasattr(itype, 'value'):
+            itype = itype.value
+        assert "interface_mismatch" in str(itype).lower()
+
+
+@pytest.mark.asyncio
+async def test_list_issues_combined_filters(report_tools, sample_marketplace):
+    """Test combined severity and type filters"""
+    result = await report_tools.list_issues(
+        sample_marketplace, "error", "interface_mismatch"
+    )
+
+    assert "error" not in result
+    # Should have command conflict errors
+    assert result["total_issues"] > 0
+
+
+@pytest.mark.asyncio
+async def test_report_markdown_has_all_sections(report_tools, sample_marketplace):
+    """Test markdown report contains all expected sections"""
+    result = await report_tools.generate_compatibility_report(
+        sample_marketplace, "markdown"
+    )
+
+    report = result["report"]
+    assert "## Summary" in report
+    assert "## Plugins" in report
+    # Compatibility section only if there are checks
+    assert "Plugin One" in report or "plugin-one" in report.lower()
+
+
+@pytest.mark.asyncio
+async def test_report_includes_suggestions(report_tools, sample_marketplace):
+    """Test that issues include suggestions"""
+    result = await report_tools.generate_compatibility_report(
+        sample_marketplace, "json"
+    )
+
+    issues = result.get("all_issues", [])
+    # Find an issue with a suggestion
+    issues_with_suggestions = [
+        i for i in issues
+        if i.get("suggestion")
+    ]
+    assert len(issues_with_suggestions) > 0

mcp-servers/contract-validator/tests/test_validation_tools.py

@@ -0,0 +1,256 @@
+"""
+Unit tests for validation tools.
+"""
+import pytest
+from pathlib import Path
+
+
+@pytest.fixture
+def validation_tools():
+    """Create ValidationTools instance"""
+    from mcp_server.validation_tools import ValidationTools
+    return ValidationTools()
+
+
+@pytest.fixture
+def plugin_a(tmp_path):
+    """Create first test plugin"""
+    plugin_dir = tmp_path / "plugin-a"
+    plugin_dir.mkdir()
+    (plugin_dir / ".claude-plugin").mkdir()
+
+    readme = plugin_dir / "README.md"
+    readme.write_text("""# Plugin A
+
+Test plugin A.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/setup-a` | Setup A |
+| `/shared-cmd` | Shared command |
+
+## Tools Summary
+
+### Core (2 tools)
+`tool_one`, `tool_two`
+""")
+    return str(plugin_dir)
+
+
+@pytest.fixture
+def plugin_b(tmp_path):
+    """Create second test plugin"""
+    plugin_dir = tmp_path / "plugin-b"
+    plugin_dir.mkdir()
+    (plugin_dir / ".claude-plugin").mkdir()
+
+    readme = plugin_dir / "README.md"
+    readme.write_text("""# Plugin B
+
+Test plugin B.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/setup-b` | Setup B |
+| `/shared-cmd` | Shared command (conflict!) |
+
+## Tools Summary
+
+### Core (2 tools)
+`tool_two`, `tool_three`
+""")
+    return str(plugin_dir)
+
+
+@pytest.fixture
+def plugin_no_conflict(tmp_path):
+    """Create plugin with no conflicts"""
+    plugin_dir = tmp_path / "plugin-c"
+    plugin_dir.mkdir()
+    (plugin_dir / ".claude-plugin").mkdir()
+
+    readme = plugin_dir / "README.md"
+    readme.write_text("""# Plugin C
+
+Test plugin C.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/unique-cmd` | Unique command |
+
+## Tools Summary
+
+### Core (1 tool)
+`unique_tool`
+""")
+    return str(plugin_dir)
+
+
+@pytest.fixture
+def claude_md_with_agents(tmp_path):
+    """Create CLAUDE.md with agent definitions"""
+    claude_md = tmp_path / "CLAUDE.md"
+    claude_md.write_text("""# CLAUDE.md
+
+### Four-Agent Model
+
+| Agent | Personality | Responsibilities |
+|-------|-------------|------------------|
+| **TestAgent** | Careful | Uses `tool_one`, `tool_two`, `missing_tool` |
+| **ValidAgent** | Thorough | Uses `tool_one` only |
+| **EmptyAgent** | Unknown | General tasks |
+""")
+    return str(claude_md)
+
+
+@pytest.mark.asyncio
+async def test_validate_compatibility_command_conflict(validation_tools, plugin_a, plugin_b):
+    """Test detection of command name conflicts"""
+    result = await validation_tools.validate_compatibility(plugin_a, plugin_b)
+
+    assert "error" not in result
+    assert result["compatible"] is False
+
+    # Find the command conflict issue
+    error_issues = [i for i in result["issues"] if i["severity"].value == "error"]
+    assert len(error_issues) > 0
+    assert any("/shared-cmd" in str(i["message"]) for i in error_issues)
+
+
+@pytest.mark.asyncio
+async def test_validate_compatibility_tool_overlap(validation_tools, plugin_a, plugin_b):
+    """Test detection of tool name overlaps"""
+    result = await validation_tools.validate_compatibility(plugin_a, plugin_b)
+
+    assert "tool_two" in result["shared_tools"]
+
+
+@pytest.mark.asyncio
+async def test_validate_compatibility_unique_tools(validation_tools, plugin_a, plugin_b):
+    """Test identification of unique tools per plugin"""
+    result = await validation_tools.validate_compatibility(plugin_a, plugin_b)
+
+    assert "tool_one" in result["a_only_tools"]
+    assert "tool_three" in result["b_only_tools"]
+
+
+@pytest.mark.asyncio
+async def test_validate_compatibility_no_conflict(validation_tools, plugin_a, plugin_no_conflict):
+    """Test compatible plugins"""
+    result = await validation_tools.validate_compatibility(plugin_a, plugin_no_conflict)
+
+    assert "error" not in result
+    assert result["compatible"] is True
+
+
+@pytest.mark.asyncio
+async def test_validate_compatibility_missing_plugin(validation_tools, plugin_a, tmp_path):
+    """Test error when plugin not found"""
+    result = await validation_tools.validate_compatibility(
+        plugin_a,
+        str(tmp_path / "nonexistent")
+    )
+
+    assert "error" in result
+
+
+@pytest.mark.asyncio
+async def test_validate_agent_refs_with_missing_tools(validation_tools, claude_md_with_agents, plugin_a):
+    """Test detection of missing tool references"""
+    result = await validation_tools.validate_agent_refs(
+        "TestAgent",
+        claude_md_with_agents,
+        [plugin_a]
+    )
+
+    assert "error" not in result
+    assert result["valid"] is False
+    assert "missing_tool" in result["tool_refs_missing"]
+
+
+@pytest.mark.asyncio
+async def test_validate_agent_refs_valid_agent(validation_tools, claude_md_with_agents, plugin_a):
+    """Test valid agent with all tools found"""
+    result = await validation_tools.validate_agent_refs(
+        "ValidAgent",
+        claude_md_with_agents,
+        [plugin_a]
+    )
+
+    assert "error" not in result
+    assert result["valid"] is True
+    assert "tool_one" in result["tool_refs_found"]
+
+
+@pytest.mark.asyncio
+async def test_validate_agent_refs_empty_agent(validation_tools, claude_md_with_agents, plugin_a):
+    """Test agent with no tool references"""
+    result = await validation_tools.validate_agent_refs(
+        "EmptyAgent",
+        claude_md_with_agents,
+        [plugin_a]
+    )
+
+    assert "error" not in result
+    # Should have info issue about undocumented references
+    info_issues = [i for i in result["issues"] if i["severity"].value == "info"]
+    assert len(info_issues) > 0
+
+
+@pytest.mark.asyncio
+async def test_validate_agent_refs_agent_not_found(validation_tools, claude_md_with_agents, plugin_a):
+    """Test error when agent not found"""
+    result = await validation_tools.validate_agent_refs(
+        "NonexistentAgent",
+        claude_md_with_agents,
+        [plugin_a]
+    )
+
+    assert "error" in result
+    assert "not found" in result["error"].lower()
+
+
+@pytest.mark.asyncio
+async def test_validate_data_flow_valid(validation_tools, tmp_path):
+    """Test data flow validation with valid flow"""
+    claude_md = tmp_path / "CLAUDE.md"
+    claude_md.write_text("""# CLAUDE.md
+
+### Four-Agent Model
+
+| Agent | Personality | Responsibilities |
+|-------|-------------|------------------|
+| **DataAgent** | Analytical | Load with `read_csv`, analyze with `describe`, export with `to_csv` |
+""")
+
+    result = await validation_tools.validate_data_flow("DataAgent", str(claude_md))
+
+    assert "error" not in result
+    assert result["valid"] is True
+
+
+@pytest.mark.asyncio
+async def test_validate_data_flow_missing_producer(validation_tools, tmp_path):
+    """Test data flow with consumer but no producer"""
+    claude_md = tmp_path / "CLAUDE.md"
+    claude_md.write_text("""# CLAUDE.md
+
+### Four-Agent Model
+
+| Agent | Personality | Responsibilities |
+|-------|-------------|------------------|
+| **BadAgent** | Careless | Just runs `describe`, `head`, `tail` without loading |
+""")
+
+    result = await validation_tools.validate_data_flow("BadAgent", str(claude_md))
+
+    assert "error" not in result
+    # Should have warning about missing producer
+    warning_issues = [i for i in result["issues"] if i["severity"].value == "warning"]
+    assert len(warning_issues) > 0