- Add model reference resolution for LLM, Question Classifier, and Parameter Extractor nodes.
- Support parsing various model reference formats, including dictionaries, UUID strings, and name strings, when `model_id` is present.
- Add warning logs for cases where model resolution fails.
- Extract duplicate model binding logic into `_get_model_by_name_or_fallback`.
- Implement logic to prioritize workspace default configuration, falling back to the tenant's first available model if not found.
- Simplify binding code for embedding, rerank, and LLM models.
- Add logic to detect tenant plan QPS limits and return a specific error message when triggered.
- Simplify boolean check in model activation quota validation.
Corrected variable reference in get_end_user_connected_config log statement. The previous code referenced app.workspace_id which could be incorrect or undefined in this context.
- Add logic to detect tenant plan QPS limits and return a specific error message when triggered.
- Simplify boolean check in model activation quota validation.
- Fix issue where tenant ID lookup from shared records failed to query the workspace correctly.
- Switch QPS counting from sliding window to simple counter to improve performance and simplify logic.
- Remove unnecessary `time` module import.
- Replace direct memory agent service calls with unified MemoryService in read endpoint
- Update query preprocessor to use new prompt format and return structured queries
- Enhance MemorySearchResult model with filtering, merging, and ID tracking capabilities
- Add intermediate outputs display for problem split, perceptual retrieval, and search results
- Fix parameter alignment and remove unused history parameter in memory agent service
- Streamline rate limit check flow by removing redundant tenant-level QPS checks.
- Restrict checks to API Key QPS and plan degradation protection only.
- Update constant naming and error message handling for consistency.
Change Body(...) to Body(None) for the message parameter which is never
used directly (request body is read via request.json() instead).
The required marker caused unnecessary 422 validation errors.
- Refactor rate limiting mechanism to limit per API Key instead of per tenant (workspace).
- Update error code logic and Redis key naming conventions.
- Adjust quota usage statistics to display the QPS of the API Key closest to its limit.
- Add `API_KEY_RATE_LIMIT_EXCEEDED` error code.
- Refactor `QuotaExceededError` to support resource type localization.
- Optimize rate limiting service by implementing the sliding window algorithm.
- Add rate limit validation for tenant plans.
- Unify quota check decorator to support both synchronous and asynchronous operations.
- Enhance quota usage statistics endpoints.
The changes remove the `ConditionGroup` abstraction and flatten condition expressions directly under `ConditionBranchConfig.expressions`. This simplifies the data model and evaluation logic, eliminating redundant grouping layers while preserving all functionality. The migration logic and group-level operators are removed as they are no longer needed.
BREAKING CHANGE: `ConditionBranchConfig.expressions` now expects a flat list of `ConditionDetail` instead of `ConditionGroup`; existing configurations must be updated to use direct condition lists.
Change list.append() to list.insert(0, ...) in extract_user_metadata_task so that newly extracted user metadata values appear at the front of each field list, maintaining a newest-first ordering.
Added support for evaluating conditions on individual fields of file objects within array[file] variables. Extended variable pool to extract fields from array elements, introduced new condition models (SubVariableConditionItem, SubVariableCondition, ConditionGroup), and added ArrayFileContainsOperator to handle contains/not_contains logic with nested sub-conditions. Includes backward compatibility migration for legacy flat expressions.
- Remove redundant `response_format` injection for VOLCANO provider since it's unsupported; rely on system prompt injection instead
- Extend system prompt JSON injection logic to cover VOLCANO and tool-enabled cases universally
- Simplify model parameter construction by removing redundant `params["model_kwargs"] = model_kwargs` assignments
- Refactor `CompatibleChatOpenAI._get_request_payload` to strip `response_format` when tools are present, avoiding strict validation errors in langchain_openai
- Fix timestamp calculation order in `datetime_tool.py` to avoid integer truncation before multiplication
Split reset_agent_config into two independent methods for getting and resetting model parameters
Add functionality to read quota configuration from environment variables to the default free tier
- Consolidate memory search services by removing separate content_search.py and perceptual_search.py
- Update model client handling in base_pipeline.py to use ModelApiKeyService for LLM client initialization
- Add new prompt files and modify existing services to support consolidated search architecture
- Refactor memory read pipeline and related services to use updated model client approach
Add a public subscription plan list endpoint that can be accessed without authentication. Enhance the returned subscription plan information fields, including multi-language support and default free plan fallback logic. Additionally, implement automatic model binding for the knowledge base service.
- Use Literal['set', 'remove'] for MetadataFieldChange.action instead of str
- Simplify field_path description to reflect current schema
- Remove redundant isinstance check in extract_user_metadata_task
- Replace UserMetadata full-object overwrite with incremental MetadataFieldChange
operations (set/remove per field path)
- Convert profile.role and profile.domain from scalar strings to lists
- Remove UserMetadataBehavioralHints and knowledge_tags fields
- Update Jinja2 prompt to instruct LLM to output incremental changes
- Update extract_user_metadata_task to apply changes via deep-copy and
per-field mutation for proper SQLAlchemy change detection
- Minor lint: remove unnecessary f-string prefixes in tasks.py
