Replace full message array re-scan with incremental tracking using useRef.
Only newly arrived messages are processed, avoiding O(n) recomputation on
every message addition. Separate maxContext computation into its own useMemo
since it depends on different data than token totals. Reset counters
automatically when conversation changes.
Replace insertion-order-dependent matching with longest-key-wins approach.
This ensures specific patterns like "kimi-k2.5" always take priority over
broader patterns like "kimi" regardless of key ordering. Update the
documentation comment to reflect the new behavior.
Update all imports of TokenConfig and EndpointTokenConfig to import
directly from librechat-data-provider instead of re-exporting through
packages/api/src/types/tokens.ts. Remove the now-unnecessary re-export
file and its barrel export.
Add TokenUsageIndicator component with circular progress ring
Create useTokenUsage hook with Jotai atom for state
Add model context window lookups to data-provider
Consolidate token utilities (output limits, TOKEN_DEFAULTS)
Display input/output tokens and percentage of context used
* fix: Update parseTextParts to handle undefined content parts
- Modified the parseTextParts function to accept an array of content parts that may include undefined values.
- Implemented optional chaining to safely check for the type of each part, preventing potential runtime errors when accessing properties of undefined elements.
* refactor: Tool Call Configuration with Session Context
- Added support for including session ID and injected files in the tool call configuration when a code session context is present.
- Improved handling of tool call configurations to accommodate additional context data, enhancing the functionality of the tool execution handler.
* chore: Update @librechat/agents to version 3.1.37 in package.json and package-lock.json
* test: Add unit tests for createToolExecuteHandler
- Introduced a new test suite for the createToolExecuteHandler function, validating the handling of session context in tool calls.
- Added tests to ensure correct passing of session IDs and injected files based on the presence of codeSessionContext.
- Included scenarios for handling multiple tool calls and ensuring non-code execution tools are unaffected by session context.
* test: Update createToolExecuteHandler tests for session context handling
- Renamed test to clarify that it checks for the absence of session context in non-code-execution tools.
- Updated assertions to ensure that session_id and _injected_files are undefined when non-code-execution tools are invoked, enhancing test accuracy.
* feat: Implement new features for Claude Opus 4.6 model
- Added support for tiered pricing based on input token count for the Claude Opus 4.6 model.
- Updated token value calculations to include inputTokenCount for accurate pricing.
- Enhanced transaction handling to apply premium rates when input tokens exceed defined thresholds.
- Introduced comprehensive tests to validate pricing logic for both standard and premium rates across various scenarios.
- Updated related utility functions and models to accommodate new pricing structure.
This change improves the flexibility and accuracy of token pricing for the Claude Opus 4.6 model, ensuring users are charged appropriately based on their usage.
* feat: Add effort field to conversation and preset schemas
- Introduced a new optional `effort` field of type `String` in both the `IPreset` and `IConversation` interfaces.
- Updated the `conversationPreset` schema to include the `effort` field, enhancing the data structure for better context management.
* chore: Clean up unused variable and comments in initialize function
* chore: update dependencies and SDK versions
- Updated @anthropic-ai/sdk to version 0.73.0 in package.json and overrides.
- Updated @anthropic-ai/vertex-sdk to version 0.14.3 in packages/api/package.json.
- Updated @librechat/agents to version 3.1.34 in packages/api/package.json.
- Refactored imports in packages/api/src/endpoints/anthropic/vertex.ts for consistency.
* chore: remove postcss-loader from dependencies
* feat: Bedrock model support for adaptive thinking configuration
- Updated .env.example to include new Bedrock model IDs for Claude Opus 4.6.
- Refactored bedrockInputParser to support adaptive thinking for Opus models, allowing for dynamic thinking configurations.
- Introduced a new function to check model compatibility with adaptive thinking.
- Added an optional `effort` field to the input schemas and updated related configurations.
- Enhanced tests to validate the new adaptive thinking logic and model configurations.
* feat: Add tests for Opus 4.6 adaptive thinking configuration
* feat: Update model references for Opus 4.6 by removing version suffix
* feat: Update @librechat/agents to version 3.1.35 in package.json and package-lock.json
* chore: @librechat/agents to version 3.1.36 in package.json and package-lock.json
* feat: Normalize inputTokenCount for spendTokens and enhance transaction handling
- Introduced normalization for promptTokens to ensure inputTokenCount does not go negative.
- Updated transaction logic to reflect normalized inputTokenCount in pricing calculations.
- Added comprehensive tests to validate the new normalization logic and its impact on transaction rates for both standard and premium models.
- Refactored related functions to improve clarity and maintainability of token value calculations.
* chore: Simplify adaptive thinking configuration in helpers.ts
- Removed unnecessary type casting for the thinking property in updatedOptions.
- Ensured that adaptive thinking is directly assigned when conditions are met, improving code clarity.
* refactor: Replace hard-coded token values with dynamic retrieval from maxTokensMap in model tests
* fix: Ensure non-negative token values in spendTokens calculations
- Updated token value retrieval to use Math.max for prompt and completion tokens, preventing negative values.
- Enhanced clarity in token calculations for both prompt and completion transactions.
* test: Add test for normalization of negative structured token values in spendStructuredTokens
- Implemented a test to ensure that negative structured token values are normalized to zero during token spending.
- Verified that the transaction rates remain consistent with the expected standard values after normalization.
* refactor: Bedrock model support for adaptive thinking and context handling
- Added tests for various alternate naming conventions of Claude models to validate adaptive thinking and context support.
- Refactored `supportsAdaptiveThinking` and `supportsContext1m` functions to utilize new parsing methods for model version extraction.
- Updated `bedrockInputParser` to handle effort configurations more effectively and strip unnecessary fields for non-adaptive models.
- Improved handling of anthropic model configurations in the input parser.
* fix: Improve token value retrieval in getMultiplier function
- Updated the token value retrieval logic to use optional chaining for better safety against undefined values.
- Added a test case to ensure that the function returns the default rate when the provided valueKey does not exist in tokenValues.
* chore: linting image context file
* refactor: Event Emission with Async Handling for Redis Ordering
- Updated emitEvent and related functions to be async, ensuring proper event ordering in Redis mode.
- Refactored multiple handlers to await emitEvent calls, improving reliability for streaming deltas.
- Enhanced GenerationJobManager to await chunk emissions, critical for maintaining sequential event delivery.
- Added tests to verify that events are delivered in strict order when using Redis, addressing previous issues with out-of-order messages.
* refactor: Clear Pending Buffers and Timeouts in RedisEventTransport
- Enhanced the cleanup process in RedisEventTransport by ensuring that pending messages and flush timeouts are cleared when the last subscriber unsubscribes.
- Updated the destroy method to also clear pending messages and flush timeouts for all streams, improving resource management and preventing memory leaks.
* refactor: Update Event Emission to Async for Improved Ordering
- Refactored GenerationJobManager and RedisEventTransport to make emitDone and emitError methods async, ensuring proper event ordering in Redis mode.
- Updated all relevant calls to await these methods, enhancing reliability in event delivery.
- Adjusted tests to verify that events are processed in the correct sequence, addressing previous issues with out-of-order messages.
* refactor: Adjust RedisEventTransport for 0-Indexed Sequence Handling
- Updated sequence handling in RedisEventTransport to be 0-indexed, ensuring consistency across event emissions and buffer management.
- Modified integration tests to reflect the new sequence logic, improving the accuracy of event processing and delivery order.
- Enhanced comments for clarity on sequence management and terminal event handling.
* chore: Add Redis dump file to .gitignore
- Included dump.rdb in .gitignore to prevent accidental commits of Redis database dumps, enhancing repository cleanliness and security.
* test: Increase wait times in RedisEventTransport integration tests for CI stability
- Adjusted wait times for subscription establishment and event propagation from 100ms and 200ms to 500ms to improve reliability in CI environments.
- Enhanced code readability by formatting promise resolution lines for better clarity.
* 🔧 refactor: Update permissions handling in updateInterfacePermissions function
- Removed explicit SHARE and SHARE_PUBLIC permissions for PROMPTS when prompts are true, simplifying the permission logic.
- Adjusted the permissions structure to conditionally include SHARE and SHARE_PUBLIC based on the type of interface configuration, enhancing maintainability and clarity in permission management.
- Updated related tests to reflect the changes in permission handling for consistency and accuracy.
* 🔧 refactor: Enhance permission configuration in updateInterfacePermissions
- Introduced a new `create` property in the permission configuration object to improve flexibility in permission management.
- Updated helper functions to accommodate the new `create` property, ensuring backward compatibility with existing boolean configurations.
- Adjusted default values for prompts and agents to include the new `create` property, enhancing the overall permission structure.
* 🧪 test: Add regression tests for SHARE/SHARE_PUBLIC permission handling
- Introduced tests to ensure existing SHARE and SHARE_PUBLIC values are preserved when using boolean configuration for agents.
- Added validation to confirm that SHARE and SHARE_PUBLIC are included in the update payload when using object configuration, enhancing the accuracy of permission management.
- These tests address potential regressions and improve the robustness of the permission handling logic in the updateInterfacePermissions function.
* fix: accessing undefined regex
- Moved the creation of the domainSeparatorRegex to the beginning of the loadToolDefinitionsWrapper function for improved clarity and performance.
- Removed redundant regex initialization within the function's loop, enhancing code efficiency and maintainability.
* 🧪 test: Enhance regression tests for SHARE/SHARE_PUBLIC permission handling
- Added a new test to ensure that SHARE and SHARE_PUBLIC permissions are preserved when using object configuration without explicit share/public keys.
- Updated existing tests to validate the inclusion of SHARE and SHARE_PUBLIC in the update payload when using object configuration, improving the robustness of permission management.
- Adjusted the updateInterfacePermissions function to conditionally include SHARE and SHARE_PUBLIC based on the presence of share/public keys in the configuration, enhancing clarity and maintainability.
* 🔧 refactor: Update permission handling in updateInterfacePermissions
- Simplified the logic for including CREATE, SHARE, and SHARE_PUBLIC permissions in the update payload based on the presence of corresponding keys in the configuration object.
- Adjusted tests to reflect the changes, ensuring that only the USE permission is updated when existing permissions are present, preserving the database values for CREATE, SHARE, and SHARE_PUBLIC.
- Enhanced clarity in comments to better explain the permission management logic.
* fix: Web Search + Image Gen Tool Context
- Added `buildWebSearchContext` function to create a structured context for web search tools, including citation format instructions.
- Updated `loadTools` and `loadToolDefinitionsWrapper` functions to utilize the new web search context, improving tool initialization and response handling.
- Introduced logic to handle image editing tools with `buildImageToolContext`, enhancing the overall tool management capabilities.
- Refactored imports in `ToolService.js` to include the new context builders for better organization and maintainability.
* fix: Trim critical output escape sequence instructions in web toolkit
- Updated the critical output escape sequence instructions in the web toolkit to include a `.trim()` method, ensuring that unnecessary whitespace is removed from the output. This change enhances the consistency and reliability of the generated output.
* ✨ test: Add MCP tool definitions tests for server name variants
- Introduced new test cases for loading MCP tools with underscored and hyphenated server names, ensuring correct functionality and handling of tool definitions.
- Validated that the tool definitions are loaded accurately based on different server name formats, enhancing test coverage for the MCP tool integration.
- Included assertions to verify the expected behavior and properties of the loaded tools, improving reliability and maintainability of the tests.
* refactor: useStepHandler to support additional delta events and buffer management
- Added support for Agents.ReasoningDeltaEvent and Agents.RunStepDeltaEvent in the TStepEvent type.
- Introduced a pendingDeltaBuffer to store deltas that arrive before their corresponding run step, ensuring they are processed in the correct order.
- Updated event handling to buffer deltas when no corresponding run step is found, improving the reliability of message processing.
- Cleared the pendingDeltaBuffer during cleanup to prevent memory leaks.
- Bumped the version of @librechat/agents to 3.1.32 across multiple package.json and package-lock.json files to ensure compatibility and access to the latest features.
- This update enhances the functionality and stability of the application by integrating the latest improvements from the @librechat/agents package.
* fix: Implement single-flight deduplication for getAllServerConfigs and optimize Redis getAll method
- Added a pending promises map in MCPServersRegistry to handle concurrent calls to getAllServerConfigs, ensuring that multiple requests for the same userId are deduplicated.
- Introduced a new fetchAllServerConfigs method to streamline the fetching process and improve performance.
- Enhanced the getAll method in ServerConfigsCacheRedis to utilize MGET for batch fetching, significantly reducing Redis roundtrips and improving efficiency.
- Added comprehensive tests for deduplication and performance optimizations, ensuring consistent results across concurrent calls and validating the new implementation.
* refactor: Enhance logging in ServerConfigsCacheRedis for getAll method
- Added debug logging to track the execution time and key retrieval in the getAll method of ServerConfigsCacheRedis.
- Improved import organization by consolidating related imports for better clarity and maintainability.
* test: Update MCPServersRegistry and ServerConfigsCacheRedis tests for call count assertions
- Modified MCPServersRegistry integration tests to assert specific call counts for cache retrieval, ensuring accurate tracking of Redis interactions.
- Refactored ServerConfigsCacheRedis integration tests to rename the test suite for clarity and improved focus on parallel fetching optimizations.
- Enhanced the getAll method in ServerConfigsCacheRedis to utilize batching for improved performance during key retrieval.
* chore: Simplify key extraction in ServerConfigsCacheRedis
- Streamlined the key extraction logic in the getAll method of ServerConfigsCacheRedis by consolidating the mapping function into a single line, enhancing code readability and maintainability.
* Add files via upload
add more padding to maskable icon
* add more padding to maskable icon
Added more padding to maskable icon, since it's broken on one ui 8 phone.
* refactor: Reorganize imports in MCPTools component
- Updated import statements in MCPTools.tsx for improved clarity and maintainability.
- Moved `useAgentPanelContext` import above others and adjusted the order of `PermissionTypes` and `Permissions` imports to enhance readability.
* chore: imports
* refactor: Update MCPToolItem component props and styles
- Added new props: onToggleDefer, onToggleSelect, and onToggleProgrammatic for improved functionality.
- Adjusted class names for DropdownMenuLabel and text spans to enhance visual consistency and clarity.
- Increased width of DropdownMenuContent for better layout.
* refactor: Update DropdownMenu styles for improved visual consistency
- Changed background color of DropdownMenuContent and DropdownMenuSubContent from secondary to primary for better alignment with design standards.
- Updated text color to ensure readability against the new background, enhancing overall user experience.
* refactor: Update Mention component styles and interaction handling
- Increased ROW_HEIGHT in Mention and PromptsCommand components for improved layout consistency.
- Enhanced MentionItem component with touch event handling to improve mobile interaction experience.
- Updated button styles to ensure better visual alignment and responsiveness.
* refactor: Enhance MentionItem component event handling and button attributes
- Updated the onClick prop type in MentionItem to support both mouse and touch events, improving mobile interaction.
- Added a button type attribute for better accessibility and compliance with HTML standards.
- Refined event handling to ensure consistent behavior across different input methods.
* refactor: Add button type attribute to MentionItem for improved accessibility
- Added a type="button" attribute to the MentionItem component to enhance accessibility and compliance with HTML standards.
- This change ensures better interaction behavior across different input methods.
* refactor: Simplify MentionItem event handling for improved clarity
- Removed touch event handling from the MentionItem component, streamlining the onClick prop to only accept mouse events.
- This change simplifies the interaction logic, enhancing maintainability while retaining functionality for mouse interactions.
* 📦 chore: Update @librechat/agents to v3.1.31
- Bumped the version of @librechat/agents across multiple package.json and package-lock.json files to ensure compatibility and access to the latest features.
- This update enhances the functionality and stability of the application by integrating the latest improvements from the @librechat/agents package.
* 📦 chore: npm audit fix - Update @isaacs/brace-expansion to v5.0.1 in package-lock.json
- Bumped the version of @isaacs/brace-expansion to 5.0.1 to incorporate the latest improvements and fixes.
- This update ensures compatibility with the latest features and enhances the stability of the application.
- Removed `forcePrompt` parameter from various configuration files including `librechat.example.yaml`, `initialize.js`, `values.yaml`, and `initialize.ts`.
- This change simplifies the configuration by eliminating unused options, enhancing clarity and maintainability across the codebase.
* ✨ feat: Add Moonshot Provider Support
- Updated the `isKnownCustomProvider` function to include `Providers.MOONSHOT` in the list of recognized custom providers.
- Enhanced the `providerConfigMap` to initialize `MOONSHOT` with the custom initialization function.
- Introduced `MoonshotIcon` component for visual representation in the UI, integrated into the `UnknownIcon` component.
- Updated various files across the API and client to support the new `MOONSHOT` provider, including configuration and response handling.
This update expands the capabilities of the application by integrating support for the Moonshot provider, enhancing both backend and frontend functionalities.
* ✨ feat: Add Moonshot/Kimi Model Pricing and Tests
- Introduced new pricing configurations for Moonshot and Kimi models in `tx.js`, including various model variations and their respective prompt and completion values.
- Expanded unit tests in `tx.spec.js` and `tokens.spec.js` to validate pricing and token limits for the newly added Moonshot/Kimi models, ensuring accurate calculations and handling of model variations.
- Updated utility functions to support the new model structures and ensure compatibility with existing functionalities.
This update enhances the pricing model capabilities and improves test coverage for the Moonshot/Kimi integration.
* ✨ feat: Enhance Token Pricing Documentation and Configuration
- Added comprehensive documentation for token pricing configuration in `tx.js` and `tokens.ts`, emphasizing the importance of key ordering for pattern matching.
- Clarified the process for defining base and specific patterns to ensure accurate pricing retrieval based on model names.
- Improved code comments to guide future additions of model families, enhancing maintainability and understanding of the pricing structure.
This update improves the clarity and usability of the token pricing configuration, facilitating better integration and future enhancements.
* chore: import order
* chore: linting
* fix: Execute code files not visible in event-driven mode
Fixes regression from #11588 where primeResources became non-mutating
but callers weren't updated to use returned values.
Changes:
- Add tool_resources to InitializedAgent type and return object
- Prime execute_code files in loadToolDefinitionsWrapper
- Pass tool_resources to loadToolDefinitionsWrapper
- Capture and return toolContextMap from loadToolsForExecution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: Reorganize imports and enhance tool loading logic in ToolService.js
- Moved domainSeparatorRegex declaration to a more appropriate location for clarity.
- Reorganized import statements for better readability and maintainability.
- Removed unused variables and streamlined the loadToolsForExecution function by eliminating the regularToolContextMap, improving performance and code clarity.
- Updated loadActionToolsForExecution to ensure consistent handling of domain separator regex.
This refactor improves the overall structure and efficiency of the ToolService module.
* fix: file search tool priming in loadToolDefinitionsWrapper
- Added functionality to prime file search tools within the loadToolDefinitionsWrapper function, enhancing the tool context map for event-driven mode.
- Implemented error handling for the file search priming process to improve robustness and logging.
- Updated the tool context map to include the newly primed file search tool, ensuring it is available for subsequent operations.
This enhancement improves the tool loading capabilities by incorporating file search tools, facilitating better integration and functionality in the application.
* chore: import order
* refactor: Update agent initialization structure for improved clarity and functionality
- Rearranged properties in the InitializedAgent object to enhance readability and maintainability.
- Moved toolRegistry to the correct position and ensured tools and attachments are set appropriately.
- This refactor improves the overall structure of the agent initialization process, facilitating better integration and future enhancements.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
- Bumped versions of several AWS SDK packages in package-lock.json and package.json to ensure compatibility and access to the latest features.
- Updated @librechat/agents to version 3.1.30 across multiple package.json files for improved functionality.
- Added fast-xml-parser dependency in package.json for enhanced XML parsing capabilities.
- Adjusted various AWS SDK dependencies to their latest versions, improving performance and security.
This update ensures that the project utilizes the most recent and stable versions of its dependencies, enhancing overall reliability and functionality.
* feat: MCP Tool Functionality with Tool Options Management
- Introduced `MCPToolItem` component for better handling of individual tool options, including selection, deferral, and programmatic invocation.
- Added `useMCPToolOptions` hook to manage tool options state, enabling deferred loading and programmatic calling for tools.
- Updated `MCPTool` component to integrate new tool options management, improving user interaction with tool selection and settings.
- Enhanced localization support for new tool options in translation files.
This update streamlines the management of MCP tools, allowing for more flexible configurations and improved user experience.
* feat: MCP Tool UI for Programmatic Tools
- Added support for programmatic tools in the MCPTool and MCPToolItem components, allowing for conditional rendering based on the availability of programmatic capabilities.
- Updated the useAgentCapabilities hook to include programmaticToolsEnabled, enhancing the capability checks for agents.
- Enhanced unit tests for useAgentCapabilities to validate the new programmatic tools functionality.
- Improved localization for programmatic tool descriptions, ensuring clarity in user interactions.
This update improves the flexibility and usability of the MCP Tool, enabling users to leverage programmatic tools effectively.
* fix: Update localization for MCP Tool UI
- Removed outdated descriptions for programmatic tool interactions in the translation file.
- Enhanced clarity in user-facing text for tool options, ensuring accurate representation of functionality.
This update improves the user experience by providing clearer instructions and descriptions for programmatic tools in the MCP Tool UI.
* chore: ESLint fix
* feat: Add unit tests for useMCPToolOptions hook
- Introduced comprehensive tests for the useMCPToolOptions hook, covering functionalities such as tool deferral and programmatic calling.
- Implemented tests for toggling tool options, ensuring correct state management and preservation of existing configurations.
- Enhanced mock implementations for useFormContext and useWatch to facilitate testing scenarios.
This update improves test coverage and reliability for the MCP Tool options management, ensuring robust validation of expected behaviors.
* fix: Adjust gap spacing in MCPToolItem component
- Updated the gap spacing in the MCPToolItem component from 1 to 1.5 for improved layout consistency.
- This change enhances the visual alignment of icons and text within the component, contributing to a better user interface experience.
* fix: Comment out programmatic tools in default agent capabilities
- Commented out the inclusion of programmatic_tools in the defaultAgentCapabilities array, as it requires the latest Code Interpreter API.
- This change ensures compatibility and prevents potential issues until the necessary API updates are integrated.
* chore: remove TOOL_CLASSIFICATION_AGENT_IDS env var blocking deferred tools
The TOOL_CLASSIFICATION_AGENT_IDS environment variable was gating
Tool Search creation even when agents had deferred tools configured
via the UI (agent tool_options). This caused agents with all MCP
tools set to defer_loading to have no tools available, since the
Tool Search tool wasn't being created.
- Remove isAgentAllowedForClassification function and its usage
- Remove early return that blocked classification features
- Update JSDoc comments to reflect current behavior
- Remove related tests from classification.spec.ts
Agent-level deferred_tools configuration now works correctly
without requiring env var configuration.
* chore: streamline classification tests and remove unused functions
- Removed deprecated tests related to environment variable configurations for tool classification.
- Simplified the classification.spec.ts file by retaining only relevant tests for the current functionality.
- Updated imports and adjusted test cases to reflect the changes in the classification module.
- Enhanced clarity in the classification utility functions by removing unnecessary comments and code.
* refactor: update ToolService to use AgentConstants for tool identification
- Replaced direct references to Constants with AgentConstants in ToolService.js for better consistency and maintainability.
- Enhanced logging in loadToolsForExecution and initializeClient to include toolRegistry size, improving debugging capabilities.
- Updated import statements in run.ts to include Constants, ensuring proper tool name checks during execution.
* chore: reorganize imports and enhance classification tests
- Updated import statements in classification.spec.ts for better clarity and organization.
- Reintroduced the getServerNameFromTool function to improve tool classification logic.
- Removed unused imports and functions to streamline the test file, enhancing maintainability.
* feat: enhance tool registry creation with additional properties
- Added toolType property to tool definitions in buildToolRegistryFromAgentOptions for improved classification.
- Included serverName assignment in tool definitions to enhance tool identification and management.
* feat: Implement token usage tracking for OpenAI and Responses controllers
- Added functionality to record token usage against user balances in OpenAIChatCompletionController and createResponse functions.
- Introduced new utility functions for managing token spending and structured token usage.
- Enhanced error handling for token recording to improve logging and debugging capabilities.
- Updated imports to include new usage tracking methods and configurations.
* test: Add unit tests for recordCollectedUsage function in usage.spec.ts
- Introduced comprehensive tests for the recordCollectedUsage function, covering various scenarios including handling empty and null collectedUsage, single and multiple usage entries, and sequential and parallel execution cases.
- Enhanced token handling tests to ensure correct calculations for both OpenAI and Anthropic formats, including cache token management.
- Improved overall test coverage for usage tracking functionality, ensuring robust validation of expected behaviors and outcomes.
* test: Add unit tests for OpenAI and Responses API controllers
- Introduced comprehensive unit tests for the OpenAIChatCompletionController and createResponse functions, focusing on the correct invocation of recordCollectedUsage for token spending.
- Enhanced tests to validate the passing of balance and transactions configuration to the recordCollectedUsage function.
- Ensured proper dependency injection of spendTokens and spendStructuredTokens in the usage recording process.
- Improved overall test coverage for token usage tracking, ensuring robust validation of expected behaviors and outcomes.
* fix: MCP OAuth tool discovery and event emission in event-driven mode
- Add discoverServerTools method to MCPManager for tool discovery when OAuth is required
- Fix OAuth event emission to send both ON_RUN_STEP and ON_RUN_STEP_DELTA events
- Fix hasSubscriber flag reset in GenerationJobManager for proper event buffering
- Add ToolDiscoveryOptions and ToolDiscoveryResult types
- Update reinitMCPServer to use new discovery method and propagate OAuth URLs
* refactor: Update ToolService and MCP modules for improved functionality
- Reintroduced Constants in ToolService for better reference management.
- Enhanced loadToolDefinitionsWrapper to handle both response and streamId scenarios.
- Updated MCP module to correct type definitions for oauthStart parameter.
- Improved MCPConnectionFactory to ensure proper disconnection handling during tool discovery.
- Adjusted tests to reflect changes in mock implementations and ensure accurate behavior during OAuth handling.
* fix: Refine OAuth handling in MCPConnectionFactory and related tests
- Updated the OAuth URL assignment logic in reinitMCPServer to prevent overwriting existing URLs.
- Enhanced error logging to provide clearer messages when tool discovery fails.
- Adjusted tests to reflect changes in OAuth handling, ensuring accurate detection of OAuth requirements without generating URLs in discovery mode.
* refactor: Clean up OAuth URL assignment in reinitMCPServer
- Removed redundant OAuth URL assignment logic in the reinitMCPServer function to streamline the tool discovery process.
- Enhanced error logging for tool discovery failures, improving clarity in debugging and monitoring.
* fix: Update response handling in ToolService for event-driven mode
- Changed the condition in loadToolDefinitionsWrapper to check for writableEnded instead of headersSent, ensuring proper event emission when the response is still writable.
- This adjustment enhances the reliability of event handling during tool execution, particularly in streaming scenarios.
