- Remove Zep Cloud dependency entirely (zep_entity_reader, zep_graph_memory_updater, zep_tools, zep_paging)
- Add local SQLite-based graph store with LLM-powered entity extraction
- Add local embeddings utility and graph tools service
- Translate all backend docstrings, LLM prompts, and UI to English
- Set English as default language, remove Chinese locale (zh.json)
- Add Ollama setup guide and configure .env.example for Ollama
- Add AGENTS.md for AI agent context
- Fix pyright type errors in models/services
- Add Nedbank Africa expansion preset
- Clean up Docker configuration and README
When the LLM returns ontology attributes as plain strings instead of
dicts, set_ontology() crashes with "TypeError: string indices must be
integers, not 'str'" at attr_def["name"].
Two-layer fix:
1. ontology_generator.py: normalize string attrs to {"name", "type",
"description"} dicts during validation, so downstream code always
receives well-formed structures.
2. graph_builder.py: add isinstance guard as a safety net in
set_ontology() for both entity and edge attribute loops.
Co-Authored-By: Octopus <liyuan851277048@icloud.com>
Background threads (graph building, simulation prep, report generation,
profile generation) now inherit the requesting user's locale preference.
Previously these fell back to 'zh' because Flask request context was
unavailable in spawned threads.
- Updated the `get_graph_data` method in `graph_builder.py` to include additional attributes such as creation time, validity periods, and episodes for nodes and edges, improving the richness of the graph data.
- Modified the detail panel in `Process.vue` to present new attributes, including properties, episodes, and timestamps, enhancing user interaction and data visibility.
- Improved styling for the detail panel to better organize and present the comprehensive information for selected nodes and edges.
- Updated `run.py` to conditionally print startup information only in the reloader process to avoid duplicate logs in debug mode.
- Modified `__init__.py` to log startup and completion messages based on the reloader process condition.
- Added warnings suppression in `graph_builder.py` for Pydantic v2 regarding Field usage.
- Revised `ontology_generator.py` to enforce strict design guidelines for entity types and relationships, ensuring compliance with new requirements.
- Improved logging behavior in `logger.py` to prevent log propagation to the root logger, avoiding duplicate outputs.
shayswrld
666ghj
octo-patch
ghostubborn