- 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.
- 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
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
When deleting an API Key, check if the associated model configuration has other active keys; if not, automatically set it to inactive.
Also optimize the model configuration query method to support multi-type queries and add sorting conditions.
* release/v0.3.0: (44 commits)
Revert "fix(web): prompt editor"
fix(web): prompt editor
fix(prompt-optimizer): handle escaped quotes in JSON parsing
fix(custom-tools): remove parameter coercion in custom tool base class
fix(core): conditionally apply thinking parameters based on model support
refactor(custom-tools): coerce query and request body parameters to schema types
fix(prompt-optimizer): support list content type in prompt optimizer
refactor(memory): unify user placeholder names and harden alias sync logic
fix(rag): replace semicolon separators with newlines in Excel parser output
fix(web): Compatible with Windows whitespace
fix(memory): make PgSQL the single source of truth for user entity aliases
refactor(rag): simplify Excel parsing logic and remove redundant chunk_token_num assignment
fix(web): Hide error message when workflow node error message equals empty string
ci(wechat-notify): add Sourcery summary extraction with Qwen fallback
fix(http-request,embedding,naive): tighten form-data validation, reduce truncation length to 8000, and disable chunking for Excel
fix(web): adjust the value of End User Name
fix(http-request): support array and file variables in form-data files upload
fix(web): change http body key name
fix(web): header user name
fix(web): calculate using the filtered breadcrumbs length
...
# Conflicts:
# web/src/views/UserMemoryDetail/Neo4j.tsx
# web/src/views/UserMemoryDetail/components/EndUserProfile.tsx
# web/src/views/UserMemoryDetail/types.ts
- Add `default_free_plan.py` to define the configuration for the Community Free Plan.
- Refactor `quota_stub.py` as a unified entry point, delegating checks to `core/quota_manager`.
- Implement core logic in `quota_manager.py` to support retrieving quotas from the premium module or configuration files.
- Update `tenant_subscription_controller` to return Community Free Plan information.
