Imposter-zx · Imposter-zx · Mar 22, 2026 · Mar 22, 2026 · Mar 22, 2026
diff --git a/.coverage b/.coverage
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
@@ -1,22 +1,24 @@
+# Pull Request Template
+
 ## Description
-Please include a summary of the change and which issue is fixed.
+Provide a clear summary of the changes and the problem being solved.
 
-Fixes # (issue)
+## Related Issues
+Fixes # (issue number)
 
-## Type of change
-- [ ] Bug fix (non-breaking change which fixes an issue)
-- [ ] New feature (non-breaking change which adds functionality)
-- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
-- [ ] This change requires a documentation update
+## Type of Change
+- [ ] Bug fix
+- [ ] New feature
+- [ ] Breaking change
+- [ ] Documentation update
 
-## How Has This Been Tested?
-Please describe the tests that you ran to verify your changes.
-- [ ] Added/Updated Unit Tests
-- [ ] Tested locally with `uv run pytest`
+## Checklist
+- [ ] I have followed the `AGENTS.md` rules.
+- [ ] My code follows the project style (black/isort).
+- [ ] I have added tests that prove my fix is effective or that my feature works.
+- [ ] New and existing unit tests pass locally.
+- [ ] I have updated the documentation.
+- [ ] Coverage is >= 90% for new code.
 
-## Checklist:
-- [ ] My code follows the style guidelines of this project (`uv run black`, `uv run isort`)
-- [ ] I have performed a self-review of my own code
-- [ ] I have commented my code, particularly in hard-to-understand areas
-- [ ] My changes generate no new warnings/linting errors (passed `uv run flake8`, `uv run mypy`)
-- [ ] New and existing unit tests pass locally with my changes
+## Screenshots (if applicable)
+Add screenshots or recordings here.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,26 +2,19 @@
 
 All notable changes to this project will be documented in this file.
 
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
-
-## [Unreleased]
-
+## [1.1.0] - 2026-03-22
 ### Added
-- **Web Dashboard**: Streamlit interface to monitor agents and workflows.
-- **Monitoring**: Prometheus metrics wrapper.
-- **Integrations**: Slack, Linear, and GitHub OAuth integrations.
-- **Core Tests**: Comprehensive test suite covering orchestrator and workflows.
-- **Real Training**: Unsloth fine-tuning via `SFTTrainer`.
-- **Real Inference**: CPU-optimized `llama-cpp` BitNet inference.
-- **CI/CD**: Expanded GitHub Actions using `uv`.
-- **Simulation**: Support for Newton physics simulations.
-- **Templates**: Add bug/feature reporting templates and PR guidelines.
-- **Security**: Added `SECURITY.md`.
-
-### Changed
-- Migrated dependency management from `requirements.txt` to `pyproject.toml` (via `uv`).
-- Standardized imports, removing `sys.path` injection hacks.
+- GitHub Integration (OAuth, PRs, Commits).
+- Slack Bot (Threads, Interactive, Slash).
+- Linear Integration (Issue creation, Status updates).
+- Error Recovery (Snapshots, Retries).
+- Advanced Superpowers Skills (Research, Audit, Optimization).
+- Advanced Context Management (Token tracking, Summarization).
+- Daytona Sandbox Integration.
+- Comprehensive Testing Suite (50+ tests).
 
-### Fixed
-- Logging configuration compatibility across different `python-json-logger` versions.
+## [1.0.0] - 2024-01-01
+### Initial Release
+- Core orchestrator engine.
+- Modal and Docker sandbox support.
+- Basic brainstorming and planning skills.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -1,15 +1,24 @@
 # Contributing to AI Dev OS
 
-First off, thanks for taking the time to contribute! 🎉
+Welcome! We are excited that you want to contribute to the AI Dev OS project.
 
-## Development Process
+## Workflow
 
-1. **Fork** the repository and clone it to your local machine.
-2. **Branch**: Create a feature branch `git checkout -b feature/your-feature-name`.
-3. **Commit**: Make sure to test your code. See the testing section.
-4. **Push**: Submit a Pull Request.
+1. Fork the repository.
+2. Create a feature branch: `feature/your-feature-name`.
+3. Follow the rules in `AGENTS.md` (mandatory).
+4. Implement your changes using TDD.
+5. Ensure all tests pass: `uv run pytest`.
+6. Submit a Pull Request.
 
-## Rules
-- You MUST follow the core rules outlined in `AGENTS.md`.
-- Test-Driven Development (TDD) is required for any logic change. 
-- Ensure you run `black`, `isort`, and `mypy` before submitting your PR.
+## Code Style
+- Use `black` for formatting.
+- Use `isort` for imports.
+- Maintain 90%+ test coverage for new code.
+
+## Submitting a PR
+Your PR must include:
+- A clear description of changes.
+- Reference to any related issues.
+- Updated documentation.
+- All tests green.
diff --git a/SECURITY.md b/SECURITY.md
@@ -2,27 +2,20 @@
 
 ## Supported Versions
 
-Only the latest `main` branch is actively supported with security updates.
-
-| Version | Supported          |
-| ------- | ------------------ |
-| v0.1.x  | :white_check_mark: |
-| legacy  | :x:                |
+We are currently only supporting security fixes for the `main` branch.
 
 ## Reporting a Vulnerability
 
-If you discover a security vulnerability within AI Dev OS, please **do not open a public issue**. 
-
-Instead, please send an e-mail to the maintainers privately or use GitHub's private vulnerability reporting feature (if enabled). We will work with you to assess and resolve the vulnerability as quickly as possible.
+If you discover a security vulnerability within this project, please do NOT open a public issue. Instead, send an email to security@example.com (replace with real email).
 
-### What to include
+Include as much information as possible:
 - A description of the vulnerability.
 - Steps to reproduce.
 - Potential impact.
-- Any mitigation strategies you've identified.
 
-### Scope
-- Core orchestration engine
-- Web Dashboard
-- Docker/Modal Sandbox isolations
-- Authentication flows
+We will acknowledge your report within 48 hours and provide a timeline for a fix.
+
+## Critical Protections
+- DO NOT commit API keys to this repository. Use environment variables.
+- All code must run in sandboxed environments (Modal, Daytona, Docker).
+- Review all third-party code before integration.
diff --git a/baseline_roadmap_tests.txt b/baseline_roadmap_tests.txt
@@ -0,0 +1,41 @@
+============================= test session starts =============================
+platform win32 -- Python 3.12.0, pytest-9.0.2, pluggy-1.6.0
+rootdir: C:\Users\HASSA\Desktop\AI-DEV-OS
+configfile: pyproject.toml
+testpaths: tests
+plugins: anyio-4.12.1, langsmith-0.7.22, asyncio-1.3.0, cov-7.0.0
+asyncio: mode=Mode.AUTO, debug=False, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function
+collected 38 items
+
+tests\test_core.py ...                                                   [  7%]
+tests\test_core_comprehensive.py .....................                   [ 63%]
+tests\test_integrations.py ...                                           [ 71%]
+tests\test_models.py ..                                                  [ 76%]
+tests\test_sandbox.py ..                                                 [ 81%]
+tests\test_skills.py ...                                                 [ 89%]
+tests\test_utils.py ....                                                 [100%]
+
+============================== warnings summary ===============================
+tests/test_core.py::test_workflow_state_logging
+tests/test_core_comprehensive.py::TestWorkflowState::test_state_initialization
+tests/test_core_comprehensive.py::TestWorkflowState::test_add_log
+tests/test_core_comprehensive.py::TestWorkflowState::test_state_transitions
+tests/test_core_comprehensive.py::TestWorkflowState::test_context_usage
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_creates_file
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_empty_agents
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\core.py:94: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    self.created_at = datetime.utcnow().isoformat()
+
+tests/test_core.py::test_workflow_state_logging
+tests/test_core_comprehensive.py::TestWorkflowState::test_add_log
+tests/test_core_comprehensive.py::TestWorkflowState::test_add_log
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\core.py:98: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    self.logs.append(f"[{datetime.utcnow().isoformat()}] {message}")
+
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_creates_file
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_empty_agents
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\core.py:181: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    "timestamp": datetime.utcnow().isoformat(),
+
+-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
+======================= 38 passed, 12 warnings in 5.81s =======================
diff --git a/coverage_report.txt b/coverage_report.txt
@@ -0,0 +1,120 @@
+============================= test session starts =============================
+platform win32 -- Python 3.12.0, pytest-9.0.2, pluggy-1.6.0
+rootdir: C:\Users\HASSA\Desktop\AI-DEV-OS
+configfile: pyproject.toml
+testpaths: tests
+plugins: anyio-4.12.1, langsmith-0.7.22, asyncio-1.3.0, cov-7.0.0
+asyncio: mode=Mode.AUTO, debug=False, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function
+collected 51 items
+
+tests\test_core.py ...                                                   [  5%]
+tests\test_core_comprehensive.py .....................                   [ 47%]
+tests\test_core_snapshot.py .F                                           [ 50%]
+tests\test_github_real.py ....                                           [ 58%]
+tests\test_integrations.py ...                                           [ 64%]
+tests\test_models.py ..                                                  [ 68%]
+tests\test_sandbox.py ..                                                 [ 72%]
+tests\test_skills.py ...                                                 [ 78%]
+tests\test_slack_bot.py ...                                              [ 84%]
+tests\test_snapshot.py ....                                              [ 92%]
+tests\test_utils.py ....                                                 [100%]
+
+================================== FAILURES ===================================
+__________________________ test_retry_on_api_failure __________________________
+
+orchestrator = <ai_dev_os.core.AIDevOSOrchestrator object at 0x0000019B0EC0AF00>
+
+    @pytest.mark.asyncio
+    async def test_retry_on_api_failure(orchestrator):
+        mock_resp = MagicMock()
+        mock_resp.content = [MagicMock(text="success result")]
+        mock_resp.usage.output_tokens = 10
+
+        orchestrator.mock_anth.messages.create.side_effect = [
+            Exception("transient error"),
+            mock_resp
+        ]
+
+        # Ensure a different request to avoid any potential (unpatched) cache hits
+        with patch("builtins.input", return_value="no"):
+            state = await orchestrator.run("unique request for retry")
+
+        assert state.design_doc == "success result"
+>       assert orchestrator.mock_anth.messages.create.call_count == 2
+E       AssertionError: assert 0 == 2
+E        +  where 0 = <MagicMock name='Anthropic().messages.create' id='1765479203376'>.call_count
+E        +    where <MagicMock name='Anthropic().messages.create' id='1765479203376'> = <MagicMock name='Anthropic().messages' id='1765479183184'>.create
+E        +      where <MagicMock name='Anthropic().messages' id='1765479183184'> = <MagicMock name='Anthropic()' id='1765479145520'>.messages
+E        +        where <MagicMock name='Anthropic()' id='1765479145520'> = <ai_dev_os.core.AIDevOSOrchestrator object at 0x0000019B0EC0AF00>.mock_anth
+
+tests\test_core_snapshot.py:58: AssertionError
+---------------------------- Captured stdout call -----------------------------
+\n[HUD] Phase: brainstorming | Context: 0.0% | Agents: none\n\n\U0001f4cb DESIGN DOCUMENT:\n\nsuccess result\n\n============================================================
+============================== warnings summary ===============================
+tests/test_core.py::test_workflow_state_logging
+tests/test_core_comprehensive.py::TestWorkflowState::test_state_initialization
+tests/test_core_comprehensive.py::TestWorkflowState::test_add_log
+tests/test_core_comprehensive.py::TestWorkflowState::test_state_transitions
+tests/test_core_comprehensive.py::TestWorkflowState::test_context_usage
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_creates_file
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_empty_agents
+tests/test_core_snapshot.py::test_run_generates_snapshots
+tests/test_core_snapshot.py::test_retry_on_api_failure
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\core.py:97: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    self.created_at = datetime.utcnow().isoformat()
+
+tests/test_core.py: 1 warning
+tests/test_core_comprehensive.py: 2 warnings
+tests/test_core_snapshot.py: 17 warnings
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\core.py:101: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    self.logs.append(f"[{datetime.utcnow().isoformat()}] {message}")
+
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_creates_file
+tests/test_core_comprehensive.py::TestClaudeHUDIntegration::test_hud_update_empty_agents
+tests/test_core_snapshot.py::test_run_generates_snapshots
+tests/test_core_snapshot.py::test_run_generates_snapshots
+tests/test_core_snapshot.py::test_run_generates_snapshots
+tests/test_core_snapshot.py::test_retry_on_api_failure
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\core.py:185: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    "timestamp": datetime.utcnow().isoformat(),
+
+tests/test_integrations.py::test_github_webhook
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\integrations\github.py:29: DeprecationWarning: Argument login_or_token is deprecated, please use auth=github.Auth.Token(...) instead
+    self.client = Github(token) if HAS_GITHUB else None
+
+tests/test_snapshot.py::test_save_snapshot_creates_file
+tests/test_snapshot.py::test_load_latest_snapshot
+tests/test_snapshot.py::test_load_latest_snapshot
+tests/test_snapshot.py::test_list_snapshots
+tests/test_snapshot.py::test_list_snapshots
+  C:\Users\HASSA\Desktop\AI-DEV-OS\src\ai_dev_os\utils\snapshot.py:26: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
+    timestamp = datetime.utcnow().strftime("%Y%m%d_%H%M%S")
+
+-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
+=============================== tests coverage ================================
+_______________ coverage: platform win32, python 3.12.0-final-0 _______________
+
+Name                                     Stmts   Miss  Cover   Missing
+----------------------------------------------------------------------
+src\ai_dev_os\__init__.py                    0      0   100%
+src\ai_dev_os\agents.py                      0      0   100%
+src\ai_dev_os\core.py                      270     36    87%   116, 153-172, 211, 281-283, 342, 397-398, 517-518, 560-594, 598
+src\ai_dev_os\hud.py                         0      0   100%
+src\ai_dev_os\integrations\__init__.py       0      0   100%
+src\ai_dev_os\integrations\github.py        56     18    68%   15-17, 27, 34-35, 43-45, 57, 63-65, 70, 77-79, 90
+src\ai_dev_os\integrations\linear.py        26     14    46%   17, 26-43, 49-55
+src\ai_dev_os\integrations\slack.py         34     10    71%   16, 38-40, 46-50, 65
+src\ai_dev_os\models.py                    194    114    41%   72-73, 95-97, 106, 117-152, 185-187, 191-210, 214-232, 239-241, 245-266, 275-293, 299-311, 318-319, 323-337, 341-343, 347-351, 355-363, 371-380, 385-389
+src\ai_dev_os\monitoring_metrics.py         43     43     0%   7-107
+src\ai_dev_os\sandbox.py                   220    141    36%   60, 68, 73, 78, 83, 96-123, 137-140, 144-150, 154-160, 164-170, 178-187, 191-196, 200-205, 209-214, 218-224, 232-260, 264-278, 282-299, 303-315, 319-327, 343-351, 356, 362-363
+src\ai_dev_os\simulation.py                 77     77     0%   7-147
+src\ai_dev_os\skills.py                     22      0   100%
+src\ai_dev_os\utils\__init__.py              0      0   100%
+src\ai_dev_os\utils\error_handling.py       21      0   100%
+src\ai_dev_os\utils\monitoring.py           23      9    61%   19-22, 28-36
+src\ai_dev_os\utils\snapshot.py             28      0   100%
+----------------------------------------------------------------------
+TOTAL                                     1014    462    54%
+=========================== short test summary info ===========================
+FAILED tests/test_core_snapshot.py::test_retry_on_api_failure - AssertionErro...
+================== 1 failed, 50 passed, 41 warnings in 8.71s ==================