Spaces:
Runtime error
Runtime error
Commit History
-
Fix task output and test infrastructureβ
- Fixed artifact generation parameter error in tools/omirl/adapter.py - Fixed metadata storage issue in tools/omirl/tables/massimi_precipitazione.py - Added comprehensive full flow test in tests/agent/full/test_full_flow.py - Added configuration viewer and navigator utilities - Added documentation for config-driven architecture - Created test infrastructure for agent refactoring validation - All tests now show formatted task output correctly connecting to LLM processing8bd860c
-
feat: Complete agent architecture refactoring and testing frameworkβ
## Major Architecture Improvements ### ποΈ Enhanced ToolCall Structure - Added explicit 'task' field to ToolCall dataclass - Eliminated confusion between tool selection and task selection - Removed deprecated 'subtask' terminology throughout codebase ### βοΈ Configuration Architecture Refactoring - Created centralized geography.yaml config (provinces, municipalities, alert zones) - Added tool_registry.yaml for tool registration and management - Enhanced llm_router_config.yaml with task-specific prompts - Eliminated legacy services/geographic/ resolver ### π§ Tool Interface Standardization - Updated OMIRL adapter to use 'task' parameter (not 'subtask') - Added default period logic: massimi_precipitazione defaults to '1h' when not specified - Enhanced parameter normalization (15m β 15' mapping) - Improved error handling and validation ### π§ͺ Comprehensive Testing Framework - Added complete end-to-end flow tests (no mocks) - Tests cover: Query β LLM Router β Tool Execution β Response Gβ¦fbd9fda
-
π― Complete OMIRL web services refactoring with workflow enhancementβ
Major changes: β’ Complete architectural refactoring: separated generic web scraping from OMIRL-specific logic β’ Fixed geographic filtering bug: corrected filters now properly applied in valori_stazioni.py β’ Enhanced agent workflow: added LLM summarization step between tool execution and response generation β’ Fixed LLM client AttributeError: added client property to expose _client attribute β’ Removed 933 lines of legacy code (browser.py, table_scraper.py) after successful migration β’ Created comprehensive new architecture with full backward compatibility New Architecture: β services/web/base.py - Abstract interfaces and base classes β services/web/generic_browser.py - Configurable browser management β services/web/generic_table.py - Flexible table extraction β services/web/configs/omirl_config.py - All OMIRL knowledge preserved β services/web/adapters/omirl_adapter.py - OMIRL implementation using generic components β services/web/compat.py - Backward compatibility layer Bug Fixes: π§ β¦36f8fda
-
docs: Update TODO for next development sessionβ
π― Current Status: - OMIRL Phase 1 refactor complete with commit 7a1055a - All tests passing (7/7 comprehensive test suites) - Real data extraction validated (199 precipitation stations) - Geographic filtering behavior confirmed (AND logic working) π Next Priorities: 1. Test cleanup and organization (HIGH) 2. Agent state and node updates (HIGH) 3. New OMIRL tasks implementation (MEDIUM) 4. Enhanced services (MEDIUM) π Ready for next development session with solid foundation established.51dab89 -
feat: Complete OMIRL Phase 1 refactor - YAML-based validation architectureβ
β¨ New Architecture Features: - Modular package structure (tables/, maps/, sensori/, shared/) - YAML-based configuration system for flexible validation - Clean separation of concerns with OMIRLFilterSet, OMIRLResult, OMIRLValidator - Comprehensive parameter validation with auto-correction and suggestions - Backward compatibility maintained for existing integrations π§ Core Components: - tools/omirl/shared/: Core data types and validation system - tools/omirl/config/: YAML configuration files (parameters, validation rules, mode/tasks) - tools/omirl/tables/valori_stazioni.py: Refactored table extraction using new architecture - tools/omirl/adapter.py: Updated to use new components while maintaining tool interface π Testing & Validation: - Comprehensive test suites (7 new test files) - All tests passing (adapter integration, architecture validation, filtering behavior) - Real data extraction validated (199 precipitation, 184 temperature, 69 Genova stations) - Geographic filtering behaviβ¦7a1055a
-
Comprehensive update: LLM Router implementation and Docker fixesβ
Major Features: - Implemented LLM Router with support for multiple providers (Gemini, OpenAI, Anthropic) - Added LLM router configuration and validation system - New agent architecture with improved state management and nodes - Enhanced geographic services and text summarization capabilities Docker Improvements: - Fixed Playwright installation using 'python -m playwright install chromium' - Added PATH configuration for app user to resolve Streamlit executable issues - Cleaned up system dependencies and removed conflicting environment variables Security & Configuration: - Added pre-commit security hooks for API key protection - Implemented comprehensive secret checking system - Enhanced .gitignore for better security coverage - Added environment configuration management - Fixed API key pattern detection to avoid false positives in code/docs Documentation: - Added deployment guide and progress tracking documents - Documented LLM router progress and integration tasks - Added security sβ¦e45fdd8