Extract every Chinese string inside backend logger.{info,warning,error,
debug,exception} calls and inside user-facing jsonify({"error|message":
...}) responses across the listed in-scope modules into
locales/{en,zh}.json under nested namespaces (log.<module>.*,
api.{error,message}.<scope>.*). Locale dictionaries stay structurally
identical; the existing flat frontend-facing keys at log.* / api.* are
left untouched. The locale helper (backend/app/utils/locale.py) now
emits a single deduplicated mirofish.locale warning per (locale, key)
pair when a translation is missing instead of silently returning the
raw key, so unknown keys are visible without crashing requests or
background tasks. A repo-root scripts/check_i18n_logs.py verifier
performs an AST-aware source scan for residual Chinese inside the
in-scope logger/jsonify calls and a recursive parity diff between
en.json and zh.json — both modes pass.
Why: backend logs and API errors previously emitted Chinese-only
strings, leaving English-speaking operators with unreadable log
aggregator output and API consumers with locale-mismatched error
messages. The t() helper and per-thread set_locale propagation already
existed; this change makes every backend caller route through them.
Closes#6
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.
Replaces the paid, rate-limited Zep Cloud service with Graphiti (graphiti-core
0.11.6) backed by a local Neo4j instance — free, unlimited, and self-hosted.
Key changes:
- Add GraphitiAdapter: drop-in Zep-compatible wrapper around Graphiti with a
persistent event-loop thread to avoid asyncio/Neo4j driver conflicts
- Switch LLM client to native GeminiClient + GeminiEmbedder (text-embedding-004
fails on Gemini compat endpoint; use google-genai SDK directly)
- Add _GeminiReranker passthrough replacing OpenAIRerankerClient (which
hardcodes gpt-4.1-nano and uses logprobs unsupported by Gemini)
- Fix Cypher queries: use s.uuid/t.uuid for edge source/target instead of
r.source_node_uuid (null property in Graphiti's schema)
- Add ontology-based entity type classifier (_classify_entity_type) so nodes
get colored by type in the D3 graph visualization instead of all being Entity
- Apply classifier in ZepEntityReader so filter_defined_entities finds entities
(previously 0 personas loaded because all labels were ['Entity'])
- Add startup recovery: auto-mark graph_building projects as graph_completed
on backend restart if Neo4j already has their data
- Add resume capability to graph build: skip already-processed episodes after
a restart (断点续传)
- Add non-blocking graph data cache with background refresh in graph.py
- Add EMBEDDING_MODEL config (default: gemini-embedding-001 for Gemini users)
- Add CLAUDE.md with project architecture and dev commands
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Added signal handling to gracefully manage shutdown events across simulation scripts, ensuring proper cleanup of resources.
- Introduced a global shutdown event to allow simulations to respond to termination signals, improving robustness.
- Suppressed warnings related to multiprocessing resource tracking to avoid unnecessary log clutter during execution.
- Updated cleanup logic in `SimulationRunner` and `ZepGraphMemoryManager` to prevent redundant calls and ensure efficient resource management.
- Enhanced logging to provide clearer feedback during shutdown processes, improving traceability.
- Added context enrichment for actions in `fetch_new_actions_from_db`, providing complete information for posts, comments, and user interactions.
- Introduced a new `_enrich_action_context` function to supplement action arguments with relevant details such as post content, author names, and comment information.
- Updated the `ZepGraphMemoryUpdater` to batch send activities by platform, improving efficiency in processing and logging.
- Enhanced logging to include detailed statistics on sent activities and skipped actions, ensuring better traceability and monitoring of the activity flow.
- Removed content truncation logic from the AgentActivity class, allowing full content to be logged for posts, comments, and quotes.
- Updated the `fetch_new_actions_from_db` function to retain complete content in action arguments, enhancing data accuracy.
- Adjusted simulation scripts to ensure that full content is sent during action creation, improving the representation of agent activities.
- Changed the activity logging format to remove simulation prefixes, ensuring clearer natural language descriptions.
- Updated the `ZepGraphMemoryUpdater` to send activities individually, enhancing the accuracy of entity and relationship extraction.
- Adjusted the README.md to reflect these changes in activity processing and Zep integration, providing clearer instructions for users.
- Added a new optional parameter `enable_graph_memory_update` to the simulation API, allowing real-time updates of agent activities to the Zep knowledge graph.
- Introduced `ZepGraphMemoryUpdater` and `ZepGraphMemoryManager` classes to handle the background processing of activity updates, ensuring efficient API calls and data management.
- Updated the README.md to include detailed instructions on the new graph memory update functionality and its configuration.
- Enhanced the simulation runner to manage the lifecycle of the graph memory updater, including starting and stopping the updater based on user configuration.
- Improved logging to track the status of graph memory updates, providing better insights into the simulation process.
Dominik Seemann
stg
ghostubborn
Abhishek Yadav
666ghj