3 Commits

Author	SHA1	Message	Date
dnviti	cebd69c780	fix: Update all pipelines to Python 3.14 ... Python 3.13 is causing installation errors in CI/CD runners. Upgrading to Python 3.14 which is the latest stable version. Changes: - pyproject.toml: Update python requirement to ^3.14 - pyproject.toml: Update MyPy python_version to 3.14 - pyproject.toml: Update Black target-version to py314 - .gitlab-ci.yml: Update PYTHON_VERSION to 3.14 - .github/workflows/build-deploy.yml: Update PYTHON_VERSION to 3.14 - .gitea/workflows/ci.yml: Update PYTHON_VERSION to 3.14 This fixes the CI/CD error: "rm: cannot remove '/opt/hostedtoolcache/Python/3.13.9/x64/lib/python3.13/__pycache__': Directory not empty" 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-19 14:22:17 +02:00
dnviti	09a9e0f066	feat: Upgrade to Python 3.13 and complete MongoDB migration ... Major improvements: - Upgrade Python from 3.10 to 3.13 with updated dependencies - Complete migration from SQLAlchemy to MongoDB/Beanie ODM - Fix all type checking errors (MyPy: 0 errors) - Fix all linting issues (Ruff: 0 errors) - Ensure code formatting (Black: 100% compliant) Technical changes: - pyproject.toml: Update to Python 3.13, modernize dependencies - models.py: Expand MongoDB models, add enums (ActionRiskLevel, TicketStatus, FeedbackType) - reliability.py: Complete rewrite from SQLAlchemy to Beanie (552 lines) - main.py: Add return type annotations, fix TicketResponse types - agent.py: Add type annotations, fix Anthropic API response handling - client.py: Add async context manager types - config.py: Add default values for required settings - database.py: Update Beanie initialization with all models All pipeline checks passing: ✅ Black formatting ✅ Ruff linting ✅ MyPy type checking 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-19 12:36:28 +02:00
LLM Automation System	1ba5ce851d	Initial commit: LLM Automation Docs & Remediation Engine v2.0 ... Features: - Automated datacenter documentation generation - MCP integration for device connectivity - Auto-remediation engine with safety checks - Multi-factor reliability scoring (0-100%) - Human feedback learning loop - Pattern recognition and continuous improvement - Agentic chat support with AI - API for ticket resolution - Frontend React with Material-UI - CI/CD pipelines (GitLab + Gitea) - Docker & Kubernetes deployment - Complete documentation and guides v2.0 Highlights: - Auto-remediation with write operations (disabled by default) - Reliability calculator with 4-factor scoring - Human feedback system for continuous learning - Pattern-based progressive automation - Approval workflow for critical actions - Full audit trail and rollback capability	2025-10-17 23:47:28 +00:00