- Remove unused `import io`
- Avoid double-encoding in save_extracted_text by caching encoded bytes
- Delegate _to_dict queries to get_ontology/get_latest_graph_external_id
- Add comment to save_ontology noting full versioning is planned for F2-3
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add `from ..config import Config` import
- Convert `_to_dict` from @staticmethod to @classmethod; it now opens a
fresh session to populate `ontology` and `graph_id` from OntologyModel
and GraphModel respectively
- Use `db.expunge(proj)` before closing sessions in create_project,
get_project and list_projects so `_to_dict` can open its own session
without nesting conflicts (SQLite StaticPool safe)
- Add five new classmethods: save_ontology, get_ontology,
save_graph_record, get_latest_graph_external_id, complete_graph_record
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Replace conftest.py with two autouse fixtures: reset_graph_factory_singleton
and reset_task_manager_singleton, plus in_memory_db fixture for tests
requiring a real DB
- Rewrite test_project_task_recovery.py to use ProjectManager + SQLite in-memory
DB instead of the removed Project dataclass (same guarantee: active_task_id
persists and defaults to None)
- Fix db.py init_db() to import db_models before Base.metadata.create_all() so
all ORM tables are registered and created on first startup
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace file-based JSON persistence with SQLAlchemy DB (ProjectModel/ProjectFileModel)
and StorageService for file content; remove Project dataclass; add 7 passing tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace in-memory dict-based TaskManager with a SQLAlchemy-backed implementation
using TaskModel. Tasks now survive process restarts. 6 new tests added and passing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Initializes the database (via init_db) and registers the StorageService
instance in app.extensions['storage'] inside create_app(). Adds get_storage()
helper for convenient access from any Flask context.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Initializes Alembic with autogenerated migration covering all 11 tables
(tasks, users, projects, project_files, ontologies, graphs, simulations,
reports, system_config, invitation_tokens, password_reset_tokens).
Adds *.db to .gitignore to exclude local SQLite dev database.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds ?format=md|pdf query param to GET /api/report/<id>/download.
PDF is generated from Markdown via fitz.Story (PyMuPDF). Also fixes
create_app() to support dict config and skip JWT auth in TESTING mode.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
graphiti-core 0.28.2 has _extract_entity_attributes required by the
monkey-patch in GraphitiBackend. Override neo4j to resolve conflict
with camel-oasis==0.2.5 which pins neo4j==5.23.0.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Extract parse_azure_url from graphiti_backend into utils/llm_client so all
services (oasis_profile_generator, simulation_config_generator, graphiti_backend,
LLMClient) strip the /chat/completions suffix and api-version before passing
base_url to the OpenAI SDK, fixing 404 errors when the full Azure endpoint URL
is set in LLM_BASE_URL.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The previous fix applied _flatten_attributes too broadly, breaking graphiti's
internal ExtractedEntities validation (lists were converted to strings).
Instead, monkey-patch only _extract_entity_attributes — the exact function
that returns entity attribute dicts to node.attributes before Neo4j write.
Lists of primitives are preserved; only dict-valued attributes are flattened.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Graphiti's attribute extraction LLM sometimes returns values wrapped in
nested dicts ({"value": "CTTI"}) instead of plain strings. Neo4j rejects
these with TypeError: "Property values can only be of primitive types".
Fix: after _AzureGenericClient gets the LLM response, validate it through
the Pydantic response_model and call _flatten_attributes() so every value
reaching Neo4j is a scalar. Also add _flatten_attributes() helper.
UI: exclude 'summary' from the Properties section of the node detail panel
since it already appears in the dedicated Summary section below.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Revert default limits back to 10 edges and 12 entities (10 specific + 2
fallback), matching Zep Cloud's maximum. Expose ONTOLOGY_MAX_ENTITY_TYPES
and ONTOLOGY_MAX_EDGE_TYPES in Config so operators can override without
touching code. Prompts now inject the live values at request time.
Also replace Chinese comments in .env.example with English equivalents.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- ontology_generator: increase entity limit to 20 (18 specific + 2 fallback),
edge types to 20 (12-20 requested); bump max_tokens to 8192
- ontology_generator: fallback type names (Person/Organization) now resolved
via i18n so Catalan gets Persona/Organització
- locales: add ontologyFallback* keys to en/zh/es/ca
- graph_builder: pass entity/edge attributes to non-Zep set_ontology (were discarded)
- graphiti_backend: _make_model builds real Pydantic fields per attribute
- graphiti_backend: _build_extraction_instructions includes per-entity attribute
hints so the LLM knows which fields to extract
- graphiti_backend: add_batch retries up to 3x on "node not found" race condition
with exponential backoff (2s, 4s) before propagating the error
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Dockerfile installs graphiti optional extras so any GRAPH_BACKEND works at runtime
- container-app.bicep adds graphBackend, neo4jUri/User/Password and llmProvider params
- 2-build-deploy.sh validates graph backend config and passes all new vars to Bicep
- config.sh.example documents new variables with inline guidance
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
When LLM_PROVIDER=gemini, LLMClient automatically uses the Google AI Studio
OpenAI-compatible endpoint instead of requiring manual base_url configuration.
An explicit base_url argument still takes precedence.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Translate all Chinese comments, docstrings, log messages, error messages,
and LLM prompt text to English across the entire backend codebase.
Locale translation files (locales/*.json) are unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
gunicorn was declared in pyproject.toml but missing from uv.lock,
so `uv sync --frozen` in the Dockerfile never installed it and the
container crashed with 'no such file or directory' on startup.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.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.
Ubuntu
BaiFu
ghostubborn