agent-os-kernel 1.1.0__py3-none-any.whl → 1.2.0__py3-none-any.whl

modules/cmvk/tests/unit/test_trace_logger.py

@@ -0,0 +1,115 @@
+"""
+Test for Feature 3: Trace Logger
+
+This test validates that the TraceLogger correctly serializes NodeState
+to JSON for research purposes.
+"""
+
+import json
+import os
+import sys
+import tempfile
+
+# Add parent directory to path for imports
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from cross_model_verification_kernel.core.trace_logger import TraceLogger
+from cross_model_verification_kernel.core.types import ExecutionTrace, NodeState
+
+
+def test_trace_logger_basic():
+    """Test basic trace logging functionality."""
+    # Create a temporary directory for test traces
+    with tempfile.TemporaryDirectory() as temp_dir:
+        logger = TraceLogger(log_dir=temp_dir)
+
+        # Create a test NodeState
+        state = NodeState(
+            input_query="Test query: Write a function to sort an array",
+            current_code="def sort_array(arr): return sorted(arr)",
+            status="verified",
+        )
+
+        # Add some history
+        trace1 = ExecutionTrace(
+            step_id=1,
+            code_generated="def sort_array(arr): return arr.sort()",
+            verifier_feedback="Failed: sort() modifies in place and returns None",
+            status="failed",
+            strategy_used="built_in_sort",
+        )
+        trace2 = ExecutionTrace(
+            step_id=2,
+            code_generated="def sort_array(arr): return sorted(arr)",
+            verifier_feedback="Success: correctly returns sorted array",
+            status="success",
+            strategy_used="built_in_sort",
+        )
+        state.history.append(trace1)
+        state.history.append(trace2)
+        state.forbidden_strategies.append("bubble_sort")
+
+        # Save trace
+        filepath = logger.save_trace("test_run", state)
+
+        # Verify file exists
+        assert os.path.exists(filepath), f"Trace file not created at {filepath}"
+
+        # Verify JSON is valid and contains expected data
+        with open(filepath) as f:
+            data = json.load(f)
+
+        assert data["input_query"] == state.input_query
+        assert data["current_code"] == state.current_code
+        assert data["status"] == state.status
+        assert len(data["history"]) == 2
+        assert data["history"][0]["status"] == "failed"
+        assert data["history"][1]["status"] == "success"
+        assert data["forbidden_strategies"] == ["bubble_sort"]
+
+        # Verify metadata
+        assert "meta" in data
+        assert data["meta"]["total_attempts"] == 2
+        assert data["meta"]["final_status"] == "solved"
+
+        print("✅ test_trace_logger_basic PASSED")
+
+
+def test_trace_logger_failed_state():
+    """Test trace logging for a failed state."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        logger = TraceLogger(log_dir=temp_dir)
+
+        state = NodeState(input_query="Impossible query", status="rejected")
+
+        # Add failed attempts
+        for i in range(3):
+            trace = ExecutionTrace(
+                step_id=i + 1,
+                code_generated=f"attempt_{i}",
+                verifier_feedback="Failed",
+                status="failed",
+                strategy_used="recursive",
+            )
+            state.history.append(trace)
+
+        state.forbidden_strategies.extend(["recursive", "iterative"])
+
+        # Save trace
+        filepath = logger.save_trace("failed_run", state)
+
+        # Verify
+        with open(filepath) as f:
+            data = json.load(f)
+
+        assert data["meta"]["total_attempts"] == 3
+        assert data["meta"]["final_status"] == "failed"
+        assert len(data["forbidden_strategies"]) == 2
+
+        print("✅ test_trace_logger_failed_state PASSED")
+
+
+if __name__ == "__main__":
+    test_trace_logger_basic()
+    test_trace_logger_failed_state()
+    print("\n✅ All tests passed!")

modules/cmvk/tests/unit/test_visualizer.py

@@ -0,0 +1,218 @@
+"""
+Test for the Visualizer Tool
+
+This test validates that the visualizer correctly loads and formats
+JSON traces for display.
+"""
+
+import json
+import os
+import sys
+import tempfile
+from io import StringIO
+
+# Add parent directory to path for imports
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from cross_model_verification_kernel.tools.visualizer import (
+    format_strategy,
+    get_latest_trace,
+    list_traces,
+    load_trace,
+    replay_trace,
+)
+
+
+def test_load_trace():
+    """Test loading a trace JSON file."""
+    # Create a temporary trace file
+    trace_data = {
+        "input_query": "Test query",
+        "current_code": "print('hello')",
+        "status": "verified",
+        "history": [
+            {
+                "step_id": 1,
+                "code_generated": "print('hello')",
+                "verifier_feedback": "PASS",
+                "status": "success",
+                "strategy_used": "simple",
+            }
+        ],
+        "forbidden_strategies": [],
+        "meta": {"timestamp": "20260121-120000", "total_attempts": 1, "final_status": "solved"},
+    }
+
+    with tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False) as f:
+        json.dump(trace_data, f)
+        temp_file = f.name
+
+    try:
+        # Load the trace
+        loaded_data = load_trace(temp_file)
+
+        # Verify data
+        assert loaded_data["input_query"] == "Test query"
+        assert loaded_data["current_code"] == "print('hello')"
+        assert len(loaded_data["history"]) == 1
+        assert loaded_data["meta"]["final_status"] == "solved"
+
+        print("✅ test_load_trace PASSED")
+    finally:
+        os.unlink(temp_file)
+
+
+def test_list_traces():
+    """Test listing trace files."""
+    # Create a temporary directory with some trace files
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Create test trace files
+        for i in range(3):
+            trace_file = os.path.join(temp_dir, f"trace_{i}.json")
+            with open(trace_file, "w") as f:
+                json.dump({"test": i}, f)
+
+        # List traces
+        traces = list_traces(temp_dir)
+
+        # Verify
+        assert len(traces) == 3
+        assert all(str(t).endswith(".json") for t in traces)
+
+        print("✅ test_list_traces PASSED")
+
+
+def test_get_latest_trace():
+    """Test getting the most recent trace file."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        import time
+
+        # Create test trace files with different timestamps
+        for i in range(3):
+            trace_file = os.path.join(temp_dir, f"trace_{i}.json")
+            with open(trace_file, "w") as f:
+                json.dump({"test": i}, f)
+            time.sleep(0.01)  # Small delay to ensure different mtimes
+
+        # Get latest
+        latest = get_latest_trace(temp_dir)
+
+        # Verify it's the last one created
+        assert latest is not None
+        assert "trace_2.json" in str(latest)
+
+        print("✅ test_get_latest_trace PASSED")
+
+
+def test_format_strategy():
+    """Test strategy name formatting."""
+    assert format_strategy("built_in_sort") == "Built In Sort"
+    assert format_strategy("bubble_sort") == "Bubble Sort"
+    assert format_strategy("two_pointer") == "Two Pointer"
+    assert format_strategy("unknown") == "Unknown Strategy"
+    assert format_strategy(None) == "Unknown Strategy"
+
+    print("✅ test_format_strategy PASSED")
+
+
+def test_replay_trace_basic():
+    """Test basic trace replay without errors."""
+    trace_data = {
+        "input_query": "Write a function to add two numbers",
+        "current_code": "def add(a, b): return a + b",
+        "status": "verified",
+        "history": [
+            {
+                "step_id": 1,
+                "code_generated": "def add(a, b): return a + b",
+                "verifier_feedback": "PASS: Simple and correct",
+                "status": "success",
+                "strategy_used": "direct",
+            }
+        ],
+        "forbidden_strategies": [],
+        "meta": {"timestamp": "20260121-120000", "total_attempts": 1, "final_status": "solved"},
+    }
+
+    # Capture output
+    old_stdout = sys.stdout
+    sys.stdout = StringIO()
+
+    try:
+        # Replay with instant speed
+        replay_trace(trace_data, speed=0, show_code=False)
+        output = sys.stdout.getvalue()
+
+        # Verify key elements are in output
+        assert "ADVERSARIAL KERNEL REPLAY" in output
+        assert "Write a function to add two numbers" in output
+        assert "GPT-4o (The Builder)" in output
+        assert "Gemini (The Prosecutor)" in output
+        assert "Kernel (The Arbiter)" in output
+        assert "SUCCESS" in output
+
+        print("✅ test_replay_trace_basic PASSED")
+    finally:
+        sys.stdout = old_stdout
+
+
+def test_replay_trace_with_failures():
+    """Test trace replay with multiple failed attempts."""
+    trace_data = {
+        "input_query": "Test problem",
+        "current_code": "final solution",
+        "status": "verified",
+        "history": [
+            {
+                "step_id": 1,
+                "code_generated": "attempt 1",
+                "verifier_feedback": "OBJECTION! Error 1",
+                "status": "failed",
+                "strategy_used": "strategy1",
+            },
+            {
+                "step_id": 2,
+                "code_generated": "attempt 2",
+                "verifier_feedback": "OBJECTION! Error 2",
+                "status": "failed",
+                "strategy_used": "strategy2",
+            },
+            {
+                "step_id": 3,
+                "code_generated": "final solution",
+                "verifier_feedback": "PASS",
+                "status": "success",
+                "strategy_used": "strategy3",
+            },
+        ],
+        "forbidden_strategies": ["strategy1", "strategy2"],
+        "meta": {"timestamp": "20260121-120000", "total_attempts": 3, "final_status": "solved"},
+    }
+
+    old_stdout = sys.stdout
+    sys.stdout = StringIO()
+
+    try:
+        replay_trace(trace_data, speed=0, show_code=False)
+        output = sys.stdout.getvalue()
+
+        # Verify multiple rounds
+        assert "Round 1 of 3" in output
+        assert "Round 2 of 3" in output
+        assert "Round 3 of 3" in output
+        assert "BANNED" in output
+        assert "Banned Strategies: 2" in output
+
+        print("✅ test_replay_trace_with_failures PASSED")
+    finally:
+        sys.stdout = old_stdout
+
+
+if __name__ == "__main__":
+    test_load_trace()
+    test_list_traces()
+    test_get_latest_trace()
+    test_format_strategy()
+    test_replay_trace_basic()
+    test_replay_trace_with_failures()
+    print("\n✅ All visualizer tests passed!")

modules/control-plane/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,82 @@
+name: Bug Report
+description: File a bug report to help us improve
+title: "[Bug]: "
+labels: ["bug", "triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report! Please provide as much detail as possible.
+  
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Steps to Reproduce
+      description: Steps to reproduce the behavior
+      placeholder: |
+        1. Initialize agent with '...'
+        2. Execute action '...'
+        3. See error
+    validations:
+      required: true
+  
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: A clear and concise description of what you expected to happen.
+    validations:
+      required: true
+  
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual Behavior
+      description: What actually happened instead.
+    validations:
+      required: true
+  
+  - type: textarea
+    id: environment
+    attributes:
+      label: Environment
+      description: Please provide relevant environment information
+      value: |
+        - OS: [e.g., Ubuntu 22.04, macOS 14, Windows 11]
+        - Python version: [e.g., 3.10.5]
+        - Agent Control Plane version: [e.g., 1.1.0]
+        - Installation method: [pip, git clone, docker]
+    validations:
+      required: true
+  
+  - type: textarea
+    id: logs
+    attributes:
+      label: Logs and Error Messages
+      description: Please paste any relevant log output or error messages
+      render: shell
+  
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Context
+      description: Add any other context about the problem here (screenshots, code snippets, etc.)
+  
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Pre-submission Checklist
+      options:
+        - label: I have searched existing issues to ensure this is not a duplicate
+          required: true
+        - label: I have provided all the required information above
+          required: true

modules/control-plane/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 💬 GitHub Discussions
+    url: https://github.com/imran-siddique/agent-control-plane/discussions
+    about: Ask questions, share ideas, and discuss with the community
+  - name: 📚 Documentation
+    url: https://github.com/imran-siddique/agent-control-plane/tree/main/docs
+    about: Read the comprehensive documentation
+  - name: 🔒 Private Security Report
+    url: https://github.com/imran-siddique/agent-control-plane/security/advisories/new
+    about: Report a security vulnerability privately

modules/control-plane/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,104 @@
+name: Feature Request
+description: Suggest a new feature or enhancement
+title: "[Feature]: "
+labels: ["enhancement", "triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for your interest in improving Agent Control Plane! 
+        
+        Before submitting:
+        - Check our [Roadmap](https://github.com/imran-siddique/agent-control-plane/blob/main/ROADMAP.md) to see if this is already planned
+        - Search [existing issues](https://github.com/imran-siddique/agent-control-plane/issues) to avoid duplicates
+        - Consider discussing in [GitHub Discussions](https://github.com/imran-siddique/agent-control-plane/discussions) first for major changes
+  
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem Statement
+      description: Is your feature request related to a problem? Please describe.
+      placeholder: I'm frustrated when...
+    validations:
+      required: true
+  
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: Describe the solution you'd like to see
+      placeholder: I would like to see...
+    validations:
+      required: true
+  
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives Considered
+      description: Describe any alternative solutions or features you've considered
+  
+  - type: dropdown
+    id: feature_area
+    attributes:
+      label: Feature Area
+      description: Which area does this feature relate to?
+      options:
+        - Core Kernel
+        - Policy Engine
+        - Execution Engine
+        - Multi-Agent Orchestration
+        - Safety & Compliance
+        - Observability
+        - Integrations (OpenAI, LangChain, MCP, A2A)
+        - Multimodal Capabilities
+        - Documentation
+        - Other
+    validations:
+      required: true
+  
+  - type: dropdown
+    id: priority
+    attributes:
+      label: Priority
+      description: How important is this feature to you?
+      options:
+        - Critical - Blocker for adoption
+        - High - Significantly improves usability
+        - Medium - Nice to have
+        - Low - Minor improvement
+    validations:
+      required: true
+  
+  - type: textarea
+    id: use_case
+    attributes:
+      label: Use Case
+      description: Describe your specific use case and how this feature would help
+      placeholder: In my scenario, I need to...
+    validations:
+      required: true
+  
+  - type: textarea
+    id: implementation
+    attributes:
+      label: Implementation Ideas
+      description: If you have ideas about how to implement this, please share
+  
+  - type: checkboxes
+    id: contribution
+    attributes:
+      label: Contribution
+      options:
+        - label: I'm willing to contribute a pull request for this feature
+  
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Pre-submission Checklist
+      options:
+        - label: I have checked the [Roadmap](https://github.com/imran-siddique/agent-control-plane/blob/main/ROADMAP.md) and this feature is not already planned
+          required: true
+        - label: I have searched existing issues to ensure this is not a duplicate
+          required: true
+        - label: I have provided sufficient detail about my use case
+          required: true

modules/control-plane/.github/ISSUE_TEMPLATE/question.yml

@@ -0,0 +1,70 @@
+name: Question or Discussion
+description: Ask a question or start a discussion
+title: "[Question]: "
+labels: ["question"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Have a question about Agent Control Plane? We're here to help!
+        
+        💡 **Tip**: Consider using [GitHub Discussions](https://github.com/imran-siddique/agent-control-plane/discussions) for open-ended questions or community discussions.
+  
+  - type: textarea
+    id: question
+    attributes:
+      label: Your Question
+      description: What would you like to know?
+      placeholder: How do I...
+    validations:
+      required: true
+  
+  - type: dropdown
+    id: category
+    attributes:
+      label: Question Category
+      description: What is your question about?
+      options:
+        - Getting Started
+        - Configuration
+        - Integration (OpenAI, LangChain, etc.)
+        - Multi-Agent Systems
+        - Safety and Compliance
+        - Performance and Scaling
+        - Troubleshooting
+        - Best Practices
+        - Architecture and Design
+        - Other
+    validations:
+      required: true
+  
+  - type: textarea
+    id: context
+    attributes:
+      label: Context
+      description: Please provide any relevant context for your question
+      placeholder: I'm trying to build...
+  
+  - type: textarea
+    id: attempted
+    attributes:
+      label: What Have You Tried?
+      description: What have you already tried or researched?
+      placeholder: I've looked at the documentation for...
+  
+  - type: textarea
+    id: code
+    attributes:
+      label: Relevant Code
+      description: If applicable, please share relevant code snippets
+      render: python
+  
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Pre-submission Checklist
+      options:
+        - label: I have searched existing issues and discussions
+          required: true
+        - label: I have reviewed the documentation
+          required: true

modules/control-plane/.github/ISSUE_TEMPLATE/security_vulnerability.yml

@@ -0,0 +1,84 @@
+name: Security Vulnerability
+description: Report a security vulnerability (private disclosure preferred)
+title: "[Security]: "
+labels: ["security", "triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ⚠️ **IMPORTANT**: For serious security vulnerabilities, please report privately via GitHub Security Advisories or email instead of creating a public issue.
+        
+        [Report a security vulnerability privately →](https://github.com/imran-siddique/agent-control-plane/security/advisories/new)
+  
+  - type: textarea
+    id: vulnerability
+    attributes:
+      label: Vulnerability Description
+      description: Describe the security issue you've discovered
+      placeholder: The system allows...
+    validations:
+      required: true
+  
+  - type: dropdown
+    id: severity
+    attributes:
+      label: Severity Assessment
+      description: How severe do you think this vulnerability is?
+      options:
+        - Critical - Remote code execution, data breach
+        - High - Privilege escalation, authentication bypass
+        - Medium - Information disclosure, DoS
+        - Low - Minor security improvement
+    validations:
+      required: true
+  
+  - type: textarea
+    id: impact
+    attributes:
+      label: Impact
+      description: What is the potential impact of this vulnerability?
+      placeholder: An attacker could...
+    validations:
+      required: true
+  
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Steps to Reproduce
+      description: How can we reproduce this issue? Please be as specific as possible.
+      placeholder: |
+        1. Configure agent with...
+        2. Send request...
+        3. Observe...
+    validations:
+      required: true
+  
+  - type: textarea
+    id: affected
+    attributes:
+      label: Affected Versions
+      description: Which versions are affected?
+      placeholder: "e.g., 1.0.0 - 1.1.0, or all versions"
+    validations:
+      required: true
+  
+  - type: textarea
+    id: mitigation
+    attributes:
+      label: Suggested Mitigation
+      description: If you have ideas for fixing this, please share
+  
+  - type: textarea
+    id: references
+    attributes:
+      label: References
+      description: Any relevant CVEs, research papers, or similar vulnerabilities
+  
+  - type: checkboxes
+    id: disclosure
+    attributes:
+      label: Disclosure
+      options:
+        - label: I understand this will be publicly visible (consider private disclosure for serious issues)
+          required: true
+        - label: I am willing to work with maintainers on coordinated disclosure