571 commits

Author	SHA1	Message	Date
Danny Avila	b5c097e5c7	⚗️ feat: Agent Context Compaction/Summarization (#12287) ... * chore: imports/types Add summarization config and package-level summarize handler contracts Register summarize handlers across server controller paths Port cursor dual-read/dual-write summary support and UI status handling Selectively merge cursor branch files for BaseClient summary content block detection (last-summary-wins), dual-write persistence, summary block unit tests, and on_summarize_status SSE event handling with started/completed/failed branches. Co-authored-by: Cursor <cursoragent@cursor.com> refactor: type safety feat: add localization for summarization status messages refactor: optimize summary block detection in BaseClient Updated the logic for identifying existing summary content blocks to use a reverse loop for improved efficiency. Added a new test case to ensure the last summary content block is updated correctly when multiple summary blocks exist. chore: add runName to chainOptions in AgentClient refactor: streamline summarization configuration and handler integration Removed the deprecated summarizeNotConfigured function and replaced it with a more flexible createSummarizeFn. Updated the summarization handler setup across various controllers to utilize the new function, enhancing error handling and configuration resolution. Improved overall code clarity and maintainability by consolidating summarization logic. feat(summarization): add staged chunk-and-merge fallback feat(usage): track summarization usage separately from messages feat(summarization): resolve prompt from config in runtime fix(endpoints): use @librechat/api provider config loader refactor(agents): import getProviderConfig from @librechat/api chore: code order feat(app-config): auto-enable summarization when configured feat: summarization config refactor(summarization): streamline persist summary handling and enhance configuration validation Removed the deprecated createDeferredPersistSummary function and integrated a new createPersistSummary function for MongoDB persistence. Updated summarization handlers across various controllers to utilize the new persistence method. Enhanced validation for summarization configuration to ensure provider, model, and prompt are properly set, improving error handling and overall robustness. refactor(summarization): update event handling and remove legacy summarize handlers Replaced the deprecated summarization handlers with new event-driven handlers for summarization start and completion across multiple controllers. This change enhances the clarity of the summarization process and improves the integration of summarization events in the application. Additionally, removed unused summarization functions and streamlined the configuration loading process. refactor(summarization): standardize event names in handlers Updated event names in the summarization handlers to use constants from GraphEvents for consistency and clarity. This change improves maintainability and reduces the risk of errors related to string literals in event handling. feat(summarization): enhance usage tracking for summarization events Added logic to track summarization usage in multiple controllers by checking the current node type. If the node indicates a summarization task, the usage type is set accordingly. This change improves the granularity of usage data collected during summarization processes. feat(summarization): integrate SummarizationConfig into AppSummarizationConfig type Enhanced the AppSummarizationConfig type by extending it with the SummarizationConfig type from librechat-data-provider. This change improves type safety and consistency in the summarization configuration structure. test: add end-to-end tests for summarization functionality Introduced a comprehensive suite of end-to-end tests for the summarization feature, covering the full LibreChat pipeline from message creation to summarization. This includes a new setup file for environment configuration and a Jest configuration specifically for E2E tests. The tests utilize real API keys and ensure proper integration with the summarization process, enhancing overall test coverage and reliability. refactor(summarization): include initial summary in formatAgentMessages output Updated the formatAgentMessages function to return an initial summary alongside messages and index token count map. This change is reflected in multiple controllers and the corresponding tests, enhancing the summarization process by providing additional context for each agent's response. refactor: move hydrateMissingIndexTokenCounts to tokenMap utility Extracted the hydrateMissingIndexTokenCounts function from the AgentClient and related tests into a new tokenMap utility file. This change improves code organization and reusability, allowing for better management of token counting logic across the application. refactor(summarization): standardize step event handling and improve summary rendering Refactored the step event handling in the useStepHandler and related components to utilize constants for event names, enhancing consistency and maintainability. Additionally, improved the rendering logic in the Summary component to conditionally display the summary text based on its availability, providing a better user experience during the summarization process. feat(summarization): introduce baseContextTokens and reserveTokensRatio for improved context management Added baseContextTokens to the InitializedAgent type to calculate the context budget based on agentMaxContextNum and maxOutputTokensNum. Implemented reserveTokensRatio in the createRun function to allow configurable context token management. Updated related tests to validate these changes and ensure proper functionality. feat(summarization): add minReserveTokens, context pruning, and overflow recovery configurations Introduced new configuration options for summarization, including minReserveTokens, context pruning settings, and overflow recovery parameters. Updated the createRun function to accommodate these new options and added a comprehensive test suite to validate their functionality and integration within the summarization process. feat(summarization): add updatePrompt and reserveTokensRatio to summarization configuration Introduced an updatePrompt field for updating existing summaries with new messages, enhancing the flexibility of the summarization process. Additionally, added reserveTokensRatio to the configuration schema, allowing for improved management of token allocation during summarization. Updated related tests to validate these new features. feat(logging): add on_agent_log event handler for structured logging Implemented an on_agent_log event handler in both the agents' callbacks and responses to facilitate structured logging of agent activities. This enhancement allows for better tracking and debugging of agent interactions by logging messages with associated metadata. Updated the summarization process to ensure proper handling of log events. fix: remove duplicate IBalanceUpdate interface declaration perf(usage): single-pass partition of collectedUsage Replace two Array.filter() passes with a single for-of loop that partitions message vs. summarization usages in one iteration. fix(BaseClient): shallow-copy message content before mutating and preserve string content Avoid mutating the original message.content array in-place when appending a summary block. Also convert string content to a text content part instead of silently discarding it. fix(ui): fix Part.tsx indentation and useStepHandler summarize-complete handling - Fix SUMMARY else-if branch indentation in Part.tsx to match chain level - Guard ON_SUMMARIZE_COMPLETE with didFinalize flag to avoid unnecessary re-renders when no summarizing parts exist - Protect against undefined completeData.summary instead of unsafe spread fix(agents): use strict enabled check for summarization handlers Change summarizationConfig?.enabled !== false to === true so handlers are not registered when summarizationConfig is undefined. chore: fix initializeClient JSDoc and move DEFAULT_RESERVE_RATIO to module scope refactor(Summary): align collapse/expand behavior with Reasoning component - Single render path instead of separate streaming vs completed branches - Use useMessageContext for isSubmitting/isLatestMessage awareness so the "Summarizing..." label only shows during active streaming - Default to collapsed (matching Reasoning), user toggles to expand - Add proper aria attributes (aria-hidden, role, aria-controls, contentId) - Hide copy button while actively streaming feat(summarization): default to self-summarize using agent's own provider/model When no summarization config is provided (neither in librechat.yaml nor on the agent), automatically enable summarization using the agent's own provider and model. The agents package already provides default prompts, so no prompt configuration is needed. Also removes the dead resolveSummarizationLLMConfig in summarize.ts (and its spec) — run.ts buildAgentContext is the single source of truth for summarization config resolution. Removes the duplicate RuntimeSummarizationConfig local type in favor of the canonical SummarizationConfig from data-provider. chore: schema and type cleanup for summarization - Add trigger field to summarizationAgentOverrideSchema so per-agent trigger overrides in librechat.yaml are not silently stripped by Zod - Remove unused SummarizationStatus type from runs.ts - Make AppSummarizationConfig.enabled non-optional to reflect the invariant that loadSummarizationConfig always sets it refactor(responses): extract duplicated on_agent_log handler refactor(run): use agents package types for summarization config Import SummarizationConfig, ContextPruningConfig, and OverflowRecoveryConfig from @librechat/agents and use them to type-check the translation layer in buildAgentContext. This ensures the config object passed to the agent graph matches what it expects. - Use `satisfies AgentSummarizationConfig` on the config object - Cast contextPruningConfig and overflowRecoveryConfig to agents types - Properly narrow trigger fields from DeepPartial to required shape feat(config): add maxToolResultChars to base endpoint schema Add maxToolResultChars to baseEndpointSchema so it can be configured on any endpoint in librechat.yaml. Resolved during agent initialization using getProviderConfig's endpoint resolution: custom endpoint config takes precedence, then the provider-specific endpoint config, then the shared `all` config. Passed through to the agents package ToolNode, which uses it to cap tool result length before it enters the context window. When not configured, the agents package computes a sensible default from maxContextTokens. fix(summarization): forward agent model_parameters in self-summarize default When no explicit summarization config exists, the self-summarize default now forwards the agent's model_parameters as the summarization parameters. This ensures provider-specific settings (e.g. Bedrock region, credentials, endpoint host) are available when the agents package constructs the summarization LLM. fix(agents): register summarization handlers by default Change the enabled gate from === true to !== false so handlers register when no explicit summarization config exists. This aligns with the self-summarize default where summarization is always on unless explicitly disabled via enabled: false. refactor(summarization): let agents package inherit clientOptions for self-summarize Remove model_parameters forwarding from the self-summarize default. The agents package now reuses the agent's own clientOptions when the summarization provider matches the agent's provider, inheriting all provider-specific settings (region, credentials, proxy, etc.) automatically. refactor(summarization): use MessageContentComplex[] for summary content Unify summary content to always use MessageContentComplex[] arrays, matching the pattern used by on_message_delta. No more string | array unions — content is always an array of typed blocks ({ type: 'text', text: '...' } for text, { type: 'reasoning_content', ... } for reasoning). Agents package: - SummaryContentBlock.content: MessageContentComplex[] (was string) - tokenCount now optional (not sent on deltas) - Removed reasoning field — reasoning is now a content block type - streamAndCollect normalizes all chunks to content block arrays - Delta events pass content blocks directly LibreChat: - SummaryContentPart.content: Agents.MessageContentComplex[] - Updated Part.tsx, Summary.tsx, useStepHandler.ts, BaseClient.js - Summary.tsx derives display text from content blocks via useMemo - Aggregator uses simple array spread refactor(summarization): enhance summary handling and text extraction - Updated BaseClient.js to improve summary text extraction, accommodating both legacy and new content formats. - Modified summarization logic to ensure consistent handling of summary content across different message formats. - Adjusted test cases in summarization.e2e.spec.js to utilize the new summary text extraction method. - Refined SSE useStepHandler to initialize summary content as an array. - Updated configuration schema by removing unused minReserveTokens field. - Cleaned up SummaryContentPart type by removing rangeHash property. These changes streamline the summarization process and ensure compatibility with various content structures. refactor(summarization): streamline usage tracking and logging - Removed direct checks for summarization nodes in ModelEndHandler and replaced them with a dedicated markSummarizationUsage function for better readability and maintainability. - Updated OpenAIChatCompletionController and responses handlers to utilize the new markSummarizationUsage function for setting usage types. - Enhanced logging functionality by ensuring the logger correctly handles different log levels. - Introduced a new useCopyToClipboard hook in the Summary component to encapsulate clipboard copy logic, improving code reusability and clarity. These changes improve the overall structure and efficiency of the summarization handling and logging processes. refactor(summarization): update summary content block documentation - Removed outdated comment regarding the last summary content block in BaseClient.js. - Added a new comment to clarify the purpose of the findSummaryContentBlock method, ensuring consistency in documentation. These changes enhance code clarity and maintainability by providing accurate descriptions of the summarization logic. refactor(summarization): update summary content structure in tests - Modified the summarization content structure in e2e tests to use an array format for text, aligning with recent changes in summary handling. - Updated test descriptions to clarify the behavior of context token calculations, ensuring consistency and clarity in the tests. These changes enhance the accuracy and maintainability of the summarization tests by reflecting the updated content structure. refactor(summarization): remove legacy E2E test setup and configuration - Deleted the e2e-setup.js and jest.e2e.config.js files, which contained legacy configurations for E2E tests using real API keys. - Introduced a new summarization.e2e.ts file that implements comprehensive E2E backend integration tests for the summarization process, utilizing real AI providers and tracking summaries throughout the run. These changes streamline the testing framework by consolidating E2E tests into a single, more robust file while removing outdated configurations. refactor(summarization): enhance E2E tests and error handling - Added a cleanup step to force exit after all tests to manage Redis connections. - Updated the summarization model to 'claude-haiku-4-5-20251001' for consistency across tests. - Improved error handling in the processStream function to capture and return processing errors. - Enhanced logging for cross-run tests and tight context scenarios to provide better insights into test execution. These changes improve the reliability and clarity of the E2E tests for the summarization process. refactor(summarization): enhance test coverage for maxContextTokens behavior - Updated run-summarization.test.ts to include a new test case ensuring that maxContextTokens does not exceed user-defined limits, even when calculated ratios suggest otherwise. - Modified summarization.e2e.ts to replace legacy UsageMetadata type with a more appropriate type for collectedUsage, improving type safety and clarity in the test setup. These changes improve the robustness of the summarization tests by validating context token constraints and refining type definitions. feat(summarization): add comprehensive E2E tests for summarization process - Introduced a new summarization.e2e.test.ts file that implements extensive end-to-end integration tests for the summarization pipeline, covering the full flow from LibreChat to agents. - The tests utilize real AI providers and include functionality to track summaries during and between runs. - Added necessary cleanup steps to manage Redis connections post-tests and ensure proper exit. These changes enhance the testing framework by providing robust coverage for the summarization process, ensuring reliability and performance under real-world conditions. fix(service): import logger from winston configuration - Removed the import statement for logger from '@librechat/data-schemas' and replaced it with an import from '~/config/winston'. - This change ensures that the logger is correctly sourced from the updated configuration, improving consistency in logging practices across the application. refactor(summary): simplify Summary component and enhance token display - Removed the unused `meta` prop from the `SummaryButton` component to streamline its interface. - Updated the token display logic to use a localized string for better internationalization support. - Adjusted the rendering of the `meta` information to improve its visibility within the `Summary` component. These changes enhance the clarity and usability of the Summary component while ensuring better localization practices. feat(summarization): add maxInputTokens configuration for summarization - Introduced a new `maxInputTokens` property in the summarization configuration schema to control the amount of conversation context sent to the summarizer, with a default value of 10000. - Updated the `createRun` function to utilize the new `maxInputTokens` setting, allowing for more flexible summarization based on agent context. These changes enhance the summarization capabilities by providing better control over input token limits, improving the overall summarization process. refactor(summarization): simplify maxInputTokens logic in createRun function - Updated the logic for the `maxInputTokens` property in the `createRun` function to directly use the agent's base context tokens when the resolved summarization configuration does not specify a value. - This change streamlines the configuration process and enhances clarity in how input token limits are determined for summarization. These modifications improve the maintainability of the summarization configuration by reducing complexity in the token calculation logic. feat(summary): enhance Summary component to display meta information - Updated the SummaryContent component to accept an optional `meta` prop, allowing for additional contextual information to be displayed above the main content. - Adjusted the rendering logic in the Summary component to utilize the new `meta` prop, improving the visibility of supplementary details. These changes enhance the user experience by providing more context within the Summary component, making it clearer and more informative. refactor(summarization): standardize reserveRatio configuration in summarization logic - Replaced instances of `reserveTokensRatio` with `reserveRatio` in the `createRun` function and related tests to unify the terminology across the codebase. - Updated the summarization configuration schema to reflect this change, ensuring consistency in how the reserve ratio is defined and utilized. - Removed the per-agent override logic for summarization configuration, simplifying the overall structure and enhancing clarity. These modifications improve the maintainability and readability of the summarization logic by standardizing the configuration parameters. * fix: circular dependency of `~/models` * chore: update logging scope in agent log handlers Changed log scope from `[agentus:${data.scope}]` to `[agents:${data.scope}]` in both the callbacks and responses controllers to ensure consistent logging format across the application. * feat: calibration ratio * refactor(tests): update summarizationConfig tests to reflect changes in enabled property Modified tests to check for the new `summarizationEnabled` property instead of the deprecated `enabled` field in the summarization configuration. This change ensures that the tests accurately validate the current configuration structure and behavior of the agents. * feat(tests): add markSummarizationUsage mock for improved test coverage Introduced a mock for the markSummarizationUsage function in the responses unit tests to enhance the testing of summarization usage tracking. This addition supports better validation of summarization-related functionalities and ensures comprehensive test coverage for the agents' response handling. * refactor(tests): simplify event handler setup in createResponse tests Removed redundant mock implementations for event handlers in the createResponse unit tests, streamlining the setup process. This change enhances test clarity and maintainability while ensuring that the tests continue to validate the correct behavior of usage tracking during on_chat_model_end events. * refactor(agents): move calibration ratio capture to finally block Reorganized the logic for capturing the calibration ratio in the AgentClient class to ensure it is executed in the finally block. This change guarantees that the ratio is captured even if the run is aborted, enhancing the reliability of the response message persistence. Removed redundant code and improved clarity in the handling of context metadata. * refactor(agents): streamline bulk write logic in recordCollectedUsage function Removed redundant bulk write operations and consolidated document handling in the recordCollectedUsage function. The logic now combines all documents into a single bulk write operation, improving efficiency and reducing error handling complexity. Updated logging to provide consistent error messages for bulk write failures. * refactor(agents): enhance summarization configuration resolution in createRun function Streamlined the summarization configuration logic by introducing a base configuration and allowing for overrides from agent-specific settings. This change improves clarity and maintainability, ensuring that the summarization configuration is consistently applied while retaining flexibility for customization. Updated the handling of summarization parameters to ensure proper integration with the agent's model and provider settings. * refactor(agents): remove unused tokenCountMap and streamline calibration ratio handling Eliminated the unused tokenCountMap variable from the AgentClient class to enhance code clarity. Additionally, streamlined the logic for capturing the calibration ratio by using optional chaining and a fallback value, ensuring that context metadata is consistently defined. This change improves maintainability and reduces potential confusion in the codebase. * refactor(agents): extract agent log handler for improved clarity and reusability Refactored the agent log handling logic by extracting it into a dedicated function, `agentLogHandler`, enhancing code clarity and reusability across different modules. Updated the event handlers in both the OpenAI and responses controllers to utilize the new handler, ensuring consistent logging behavior throughout the application. * test: add summarization event tests for useStepHandler Implemented a series of tests for the summarization events in the useStepHandler hook. The tests cover scenarios for ON_SUMMARIZE_START, ON_SUMMARIZE_DELTA, and ON_SUMMARIZE_COMPLETE events, ensuring proper handling of summarization logic, including message accumulation and finalization. This addition enhances test coverage and validates the correct behavior of the summarization process within the application. * refactor(config): update summarizationTriggerSchema to use enum for type validation Changed the type of the `type` field in the summarizationTriggerSchema from a string to an enum with a single value 'token_count'. This modification enhances type safety and ensures that only valid types are accepted in the configuration, improving overall clarity and maintainability of the schema. * test(usage): add bulk write tests for message and summarization usage Implemented tests for the bulk write functionality in the recordCollectedUsage function, covering scenarios for combined message and summarization usage, summarization-only usage, and message-only usage. These tests ensure correct document handling and token rollup calculations, enhancing test coverage and validating the behavior of the usage tracking logic. * refactor(Chat): enhance clipboard copy functionality and type definitions in Summary component Updated the Summary component to improve the clipboard copy functionality by handling clipboard permission errors. Refactored type definitions for SummaryProps to use a more specific type, enhancing type safety. Adjusted the SummaryButton and FloatingSummaryBar components to accept isCopied and onCopy props, promoting better separation of concerns and reusability. * chore(translations): remove unused "Expand Summary" key from English translations Deleted the "Expand Summary" key from the English translation file to streamline the localization resources and improve clarity in the user interface. This change helps maintain an organized and efficient translation structure. * refactor: adjust token counting for Claude model to account for API discrepancies Implemented a correction factor for token counting when using the Claude model, addressing discrepancies between Anthropic's API and local tokenizer results. This change ensures accurate token counts by applying a scaling factor, improving the reliability of token-related functionalities. * refactor(agents): implement token count adjustment for Claude model messages Added a method to adjust token counts for messages processed by the Claude model, applying a correction factor to align with API expectations. This enhancement improves the accuracy of token counting, ensuring reliable functionality when interacting with the Claude model. * refactor(agents): token counting for media content in messages Introduced a new method to estimate token costs for image and document blocks in messages, improving the accuracy of token counting. This enhancement ensures that media content is properly accounted for, particularly for the Claude model, by integrating additional token estimation logic for various content types. Updated the token counting function to utilize this new method, enhancing overall reliability and functionality. * chore: fix missing import * fix(agents): clamp baseContextTokens and document reserve ratio change Prevent negative baseContextTokens when maxOutputTokens exceeds the context window (misconfigured models). Document the 10%→5% default reserve ratio reduction introduced alongside summarization. * fix(agents): include media tokens in hydrated token counts Add estimateMediaTokensForMessage to createTokenCounter so the hydration path (used by hydrateMissingIndexTokenCounts) matches the precomputed path in AgentClient.getTokenCountForMessage. Without this, messages containing images or documents were systematically undercounted during hydration, risking context window overflow. Add 34 unit tests covering all block-type branches of estimateMediaTokensForMessage. * fix(agents): include summarization output tokens in usage return value The returned output_tokens from recordCollectedUsage now reflects all billed LLM calls (message + summarization). Previously, summarization completions were billed but excluded from the returned metadata, causing a discrepancy between what users were charged and what the response message reported. * fix(tests): replace process.exit with proper Redis cleanup in e2e test The summarization E2E test used process.exit(0) to work around a Redis connection opened at import time, which killed the Jest runner and bypassed teardown. Use ioredisClient.quit() and keyvRedisClient.disconnect() for graceful cleanup instead. * fix(tests): update getConvo imports in OpenAI and response tests Refactor test files to import getConvo from the main models module instead of the Conversation submodule. This change ensures consistency across tests and simplifies the import structure, enhancing maintainability. * fix(clients): improve summary text validation in BaseClient Refactor the summary extraction logic to ensure that only non-empty summary texts are considered valid. This change enhances the robustness of the message processing by utilizing a dedicated method for summary text retrieval, improving overall reliability. * fix(config): replace z.any() with explicit union in summarization schema Model parameters (temperature, top_p, etc.) are constrained to primitive types rather than the policy-violating z.any(). * refactor(agents): deduplicate CLAUDE_TOKEN_CORRECTION constant Export from the TS source in packages/api and import in the JS client, eliminating the static class property that could drift out of sync. * refactor(agents): eliminate duplicate selfProvider in buildAgentContext selfProvider and provider were derived from the same expression with different type casts. Consolidated to a single provider variable. * refactor(agents): extract shared SSE handlers and restrict log levels - buildSummarizationHandlers() factory replaces triplicated handler blocks across responses.js and openai.js - agentLogHandlerObj exported from callbacks.js for consistent reuse - agentLogHandler restricted to an allowlist of safe log levels (debug, info, warn, error) instead of accepting arbitrary strings * fix(SSE): batch summarize deltas, add exhaustiveness check, conditional error announcement - ON_SUMMARIZE_DELTA coalesces rapid-fire renders via requestAnimationFrame instead of calling setMessages per chunk - Exhaustive never-check on TStepEvent catches unhandled variants at compile time when new StepEvents are added - ON_SUMMARIZE_COMPLETE error announcement only fires when a summary part was actually present and removed * feat(agents): persist instruction overhead in contextMeta and seed across runs Extend contextMeta with instructionOverhead and toolCount so the provider-observed instruction overhead is persisted on the response message and seeded into the pruner on subsequent runs. This enables the pruner to use a calibrated budget from the first call instead of waiting for a provider observation, preventing the ratio collapse caused by local tokenizer overestimating tool schema tokens. The seeded overhead is only used when encoding and tool count match between runs, ensuring stale values from different configurations are discarded. * test(agents): enhance OpenAI test mocks for summarization handlers Updated the OpenAI test suite to include additional mock implementations for summarization handlers, including buildSummarizationHandlers, markSummarizationUsage, and agentLogHandlerObj. This improves test coverage and ensures consistent behavior during testing. * fix(agents): address review findings for summarization v2 Cancel rAF on unmount to prevent stale Recoil writes from dead component context. Clear orphaned summarizing:true parts when ON_SUMMARIZE_COMPLETE arrives without a summary payload. Add null guard and safe spread to agentLogHandler. Handle Anthropic-format base64 image/* documents in estimateMediaTokensForMessage. Use role="region" for expandable summary content. Add .describe() to contextMeta Zod fields. Extract duplicate usage loop into helper. * refactor: simplify contextMeta to calibrationRatio + encoding only Remove instructionOverhead and toolCount from cross-run persistence — instruction tokens change too frequently between runs (prompt edits, tool changes) for a persisted seed to be reliable. The intra-run calibration in the pruner still self-corrects via provider observations. contextMeta now stores only the tokenizer-bias ratio and encoding, which are stable across instruction changes. * test(SSE): enhance useStepHandler tests for ON_SUMMARIZE_COMPLETE behavior Updated the test for ON_SUMMARIZE_COMPLETE to clarify that it finalizes the existing part with summarizing set to false when the summary is undefined. Added assertions to verify the correct behavior of message updates and the state of summary parts. * refactor(BaseClient): remove handleContextStrategy and truncateToolCallOutputs functions Eliminated the handleContextStrategy method from BaseClient to streamline message handling. Also removed the truncateToolCallOutputs function from the prompts module, simplifying the codebase and improving maintainability. * refactor: add AGENT_DEBUG_LOGGING option and refactor token count handling in BaseClient Introduced AGENT_DEBUG_LOGGING to .env.example for enhanced debugging capabilities. Refactored token count handling in BaseClient by removing the handleTokenCountMap method and simplifying token count updates. Updated AgentClient to log detailed token count recalculations and adjustments, improving traceability during message processing. * chore: update dependencies in package-lock.json and package.json files Bumped versions of several dependencies, including @librechat/agents to ^3.1.62 and various AWS SDK packages to their latest versions. This ensures compatibility and incorporates the latest features and fixes. * chore: imports order * refactor: extract summarization config resolution from buildAgentContext * refactor: rename and simplify summarization configuration shaping function * refactor: replace AgentClient token counting methods with single-pass pure utility Extract getTokenCount() and getTokenCountForMessage() from AgentClient into countFormattedMessageTokens(), a pure function in packages/api that handles text, tool_call, image, and document content types in one loop. - Decompose estimateMediaTokensForMessage into block-level helpers (estimateImageDataTokens, estimateImageBlockTokens, estimateDocumentBlockTokens) shared by both estimateMediaTokensForMessage and the new single-pass function - Remove redundant per-call getEncoding() resolution (closure captures once) - Remove deprecated gpt-3.5-turbo-0301 model branching - Drop this.getTokenCount guard from BaseClient.sendMessage * refactor: streamline token counting in createTokenCounter function Simplified the createTokenCounter function by removing the media token estimation and directly calculating the token count. This change enhances clarity and performance by consolidating the token counting logic into a single pass, while maintaining compatibility with Claude's token correction. * refactor: simplify summarization configuration types Removed the AppSummarizationConfig type and directly used SummarizationConfig in the AppConfig interface. This change streamlines the type definitions and enhances consistency across the codebase. * chore: import order * fix: summarization event handling in useStepHandler - Cancel pending summarizeDeltaRaf in clearStepMaps to prevent stale frames firing after map reset or component unmount - Move announcePolite('summarize_completed') inside the didFinalize guard so screen readers only announce when finalization actually occurs - Remove dead cleanup closure returned from stepHandler useCallback body that was never invoked by any caller * fix: estimate tokens for non-PDF/non-image base64 document blocks Previously estimateDocumentBlockTokens returned 0 for unrecognized MIME types (e.g. text/plain, application/json), silently underestimating context budget. Fall back to character-based heuristic or countTokens. * refactor: return cloned usage from markSummarizationUsage Avoid mutating LangChain's internal usage_metadata object by returning a shallow clone with the usage_type tag. Update all call sites in callbacks, openai, and responses controllers to use the returned value. * refactor: consolidate debug logging loops in buildMessages Merge the two sequential O(n) debug-logging passes over orderedMessages into a single pass inside the map callback where all data is available. * refactor: narrow SummaryContentPart.content type Replace broad Agents.MessageContentComplex[] with the specific Array<{ type: ContentTypes.TEXT; text: string }> that all producers and consumers already use, improving compile-time safety. * refactor: use single output array in recordCollectedUsage Have processUsageGroup append to a shared array instead of returning separate arrays that are spread into a third, reducing allocations. * refactor: use for...in in hydrateMissingIndexTokenCounts Replace Object.entries with for...in to avoid allocating an intermediate tuple array during token map hydration.	2026-03-21 14:28:56 -04:00
Danny Avila	58f128bee7	🗑️ chore: Remove Deprecated Project Model and Associated Fields (#11773) ... * chore: remove projects and projectIds usage * chore: empty line linting * chore: remove isCollaborative property across agent models and related tests - Removed the isCollaborative property from agent models, controllers, and tests, as it is deprecated in favor of ACL permissions. - Updated related validation schemas and data provider types to reflect this change. - Ensured all references to isCollaborative were stripped from the codebase to maintain consistency and clarity.	2026-03-21 14:28:53 -04:00
Danny Avila	0736ff2668	✨ v0.8.4 (#12339) ... * 🔖 chore: Bump version to v0.8.4 - App version: v0.8.4-rc1 → v0.8.4 - @librechat/api: 1.7.26 → 1.7.27 - @librechat/client: 0.4.55 → 0.4.56 - librechat-data-provider: 0.8.400 → 0.8.401 - @librechat/data-schemas: 0.0.39 → 0.0.40 * chore: bun.lock file bumps	2026-03-20 18:01:00 -04:00
Pol Burkardt Freire	7e74165c3c	📖 feat: Add Native ODT Document Parser Support (#12303) ... * fix: add ODT support to native document parser * fix: replace execSync with jszip for ODT parsing * docs: update documentParserMimeTypes comment to include odt * fix: improve ODT XML extraction and add empty.odt fixture - Scope extraction to <office:body> to exclude metadata/style nodes - Map </text:p> and </text:h> closings to newlines, preserving paragraph structure instead of collapsing everything to a single line - Handle <text:line-break/> as explicit newlines - Strip remaining tags, normalize horizontal whitespace, cap consecutive blank lines at one - Regenerate sample.odt as a two-paragraph fixture so the test exercises multi-paragraph output - Add empty.odt fixture and test asserting 'No text found in document' * fix: address review findings in ODT parser - Use static `import JSZip from 'jszip'` instead of dynamic import; jszip is CommonJS-only with no ESM/Jest-isolation concern (F1) - Decode the five standard XML entities after tag-stripping so documents with &, <, >, ", ' send correct text to the LLM (F2) - Remove @types/jszip devDependency; jszip ships bundled declarations and @types/jszip is a stale 2020 stub that would shadow them (F3) - Handle <text:tab/> → \t and <text:s .../> → ' ' before the generic tag stripper so tab-aligned and multi-space content is preserved (F4) - Add sample-entities.odt fixture and test covering entity decoding, tab, and spacing-element handling (F5) - Rename 'throws for empty odt' → 'throws for odt with no extractable text' to distinguish from a zero-byte/corrupt file case (F8) * fix: add decompressed content size cap to odtToText (F6) Reads uncompressed entry sizes from the JSZip internal metadata before extracting any content. Throws if the total exceeds 50MB, preventing a crafted ODT with a high-ratio compressed payload from exhausting heap. Adds a corresponding test using a real DEFLATE-compressed ZIP (~51KB on disk, 51MB uncompressed) to verify the guard fires before any extraction. * fix: add java to codeTypeMapping for file upload support .java files were rejected with "Unable to determine file type" because browsers send an empty MIME type for them and codeTypeMapping had no 'java' entry for inferMimeType() to fall back on. text/x-java was already present in all five validation lists (fullMimeTypesList, codeInterpreterMimeTypesList, retrievalMimeTypesList, textMimeTypes, retrievalMimeTypes), so mapping to it (not text/plain) ensures .java uploads work for both File Search and Code Interpreter. Closes #12307 * fix: address follow-up review findings (A-E) A: regenerate package-lock.json after removing @types/jszip from package.json; without this npm ci was still installing the stale 2020 type stubs and TypeScript was resolving against them B: replace dynamic import('jszip') in the zip-bomb test with the same static import already used in production; jszip is CJS-only with no ESM/Jest isolation concern C: document that the _data.uncompressedSize guard fails open if jszip renames the private field (accepted limitation, test would catch it) D: rename 'preserves tabs' test to 'normalizes tab and spacing elements to spaces' since <text:tab> is collapsed to a space, not kept as \t E: fix test.each([ formatting artifact (missing newline after '[') --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-03-19 15:49:52 -04:00
Danny Avila	b189972381	🎭 fix: Set Explicit Permission Defaults for USER Role in roleDefaults (#12308) ... * fix: set explicit permission defaults for USER role in roleDefaults Previously several permission types for the USER role had empty objects in roleDefaults, causing the getPermissionValue fallback to resolve SHARE/CREATE via the zod schema defaults on fresh installs. This silently granted users MCP server creation ability and left share permissions ambiguous. Sets explicit defaults for all multi-field permission types: - PROMPTS/AGENTS: USE and CREATE true, SHARE false - MCP_SERVERS: USE true, CREATE/SHARE false - REMOTE_AGENTS: all false Adds regression tests covering the exact reported scenarios (fresh install with `agents: { use: true }`, restart preserving admin-panel overrides) and structural guards against future permission schema expansions missing explicit USER defaults. Closes #12306. * fix: guard MCP_SERVERS.CREATE against configDefaults fallback + add migration The roleDefaults fix alone was insufficient: loadDefaultInterface propagates configDefaults.mcpServers.create=true as tier-1 in getPermissionValue, overriding the roleDefault of false. This commit: - Adds conditional guards for MCP_SERVERS.CREATE and REMOTE_AGENTS.CREATE matching the existing AGENTS/PROMPTS pattern (only include CREATE when explicitly configured in yaml OR on fresh install) - Uses raw interfaceConfig for MCP_SERVERS.CREATE tier-1 instead of loadedInterface (which includes configDefaults fallback) - Adds one-time migration backfill: corrects existing MCP_SERVERS.CREATE=true for USER role in DB when no explicit yaml config is present - Adds restart-scenario and migration regression tests for MCP_SERVERS - Cleans up roles.spec.ts: for..of loops, Permissions[] typing, Set for lookups, removes unnecessary aliases, improves JSDoc for exclusion list - Fixes misleading test name for agents regression test - Removes redundant not.toHaveProperty assertions after strict toEqual * fix: use raw interfaceConfig for REMOTE_AGENTS.CREATE tier-1 (consistency) Aligns REMOTE_AGENTS.CREATE with the MCP_SERVERS.CREATE fix — reads from raw interfaceConfig instead of loadedInterface to prevent a future configDefaults fallback from silently overriding the roleDefault.	2026-03-19 14:52:06 -04:00
Danny Avila	9cb5ac63f8	🫧 refactor: Clear Drafts and Surface Error on Expired SSE Stream (#12309) ... * refactor: error handling in useResumableSSE for 404 responses - Added logic to clear drafts from localStorage when a 404 error occurs. - Integrated errorHandler to notify users of the error condition. - Introduced comprehensive tests to validate the new behavior, ensuring drafts are cleared and error handling is triggered correctly.C * feat: add STREAM_EXPIRED error handling and message localization - Introduced handling for STREAM_EXPIRED errors in useResumableSSE, updating errorHandler to provide relevant feedback. - Added a new error message for STREAM_EXPIRED in translation files for user notifications. - Updated tests to ensure proper error handling and message verification for STREAM_EXPIRED scenarios. * refactor: replace clearDraft with clearAllDrafts utility - Removed the clearDraft function from useResumableSSE and useSSE hooks, replacing it with the new clearAllDrafts utility for better draft management. - Updated localStorage interactions to ensure both text and file drafts are cleared consistently for a conversation. - Enhanced code readability and maintainability by centralizing draft clearing logic.	2026-03-19 14:51:28 -04:00
Danny Avila	1e1a3a8f8d	✨ v0.8.4-rc1 (#12285) ... - App version: v0.8.3 → v0.8.4-rc1 - @librechat/api: 1.7.25 → 1.7.26 - @librechat/client: 0.4.54 → 0.4.55 - librechat-data-provider: 0.8.302 → 0.8.400 - @librechat/data-schemas: 0.0.38 → 0.0.39	2026-03-17 16:08:48 -04:00
Danny Avila	2f09d29c71	🛂 fix: Validate types Query Param in People Picker Access Middleware (#12276) ... * 🛂 fix: Validate `types` query param in people picker access middleware checkPeoplePickerAccess only inspected `req.query.type` (singular), allowing callers to bypass type-specific permission checks by using the `types` (plural) parameter accepted by the controller. Now both `type` and `types` are collected and each requested principal type is validated against the caller's role permissions. * 🛂 refactor: Hoist valid types constant, improve logging, and add edge-case tests - Hoist VALID_PRINCIPAL_TYPES to module-level Set to avoid per-request allocation - Include both `type` and `types` in error log for debuggability - Restore detailed JSDoc documenting per-type permission requirements - Add missing .json() assertion on partial-denial test - Add edge-case tests: all-invalid types, empty string types, PrincipalType.PUBLIC * 🏷️ fix: Align TPrincipalSearchParams with actual controller API The stale type used `type` (singular) but the controller and all callers use `types` (plural array). Aligns with PrincipalSearchParams in types/queries.ts.	2026-03-17 02:46:11 -04:00
Danny Avila	951d261f5c	🧯 fix: Prevent Env-Variable Exfil. via Placeholder Injection (#12260) ... * 🔒 fix: Resolve env vars before body placeholder expansion to prevent secret exfiltration Body placeholders ({{LIBRECHAT_BODY_*}}) were substituted before extractEnvVariable ran, allowing user-controlled body fields containing ${SECRET} patterns to be expanded into real environment values in outbound headers. Reorder so env vars resolve first, preventing untrusted input from triggering env expansion. * 🛡️ fix: Block sensitive infrastructure env vars from placeholder resolution Add isSensitiveEnvVar blocklist to extractEnvVariable so that internal infrastructure secrets (JWT_SECRET, JWT_REFRESH_SECRET, CREDS_KEY, CREDS_IV, MEILI_MASTER_KEY, MONGO_URI, REDIS_URI, REDIS_PASSWORD) can never be resolved via ${VAR} expansion — even if an attacker manages to inject a placeholder pattern. Uses exact-match set (not substring patterns) to avoid breaking legitimate operator config that references OAuth/API secrets in MCP and custom endpoint configurations. * 🧹 test: Rename ANOTHER_SECRET test fixture to ANOTHER_VALUE Avoid using SECRET-containing names for non-sensitive test fixtures to prevent confusion with the new isSensitiveEnvVar blocklist. * 🔒 fix: Resolve env vars before all user-controlled substitutions in processSingleValue Move extractEnvVariable to run on the raw admin-authored template BEFORE customUserVars, user fields, OIDC tokens, and body placeholders. Previously env resolution ran after customUserVars, so a user setting a custom MCP variable to "${SECRET}" could still trigger env expansion. Now env vars are resolved strictly on operator config, and all subsequent user-controlled substitutions cannot introduce ${VAR} patterns that would be expanded. Gated by !dbSourced so DB-stored servers continue to skip env resolution. Adds a security-invariant comment documenting the ordering requirement. * 🧪 test: Comprehensive security regression tests for placeholder injection - Cover all three body fields (conversationId, parentMessageId, messageId) - Add user-field injection test (user.name containing ${VAR}) - Add customUserVars injection test (MY_TOKEN = "${VAR}") - Add processMCPEnv injection tests for body and customUserVars paths - Remove redundant process.env setup/teardown already handled by beforeEach/afterEach * 🧹 chore: Add REDIS_PASSWORD to blocklist integration test; document customUserVars gate	2026-03-16 08:48:24 -04:00
Danny Avila	f7ab5e645a	🫷 fix: Validate User-Provided Base URL in Endpoint Init (#12248) ... * 🛡️ fix: Block SSRF via user-provided baseURL in endpoint initialization User-provided baseURL values (when endpoint is configured with `user_provided`) were passed through to the OpenAI SDK without validation. Combined with `directEndpoint`, this allowed arbitrary server-side requests to internal/metadata URLs. Adds `validateEndpointURL` that checks against known SSRF targets and DNS-resolves hostnames to block private IPs. Applied in both custom and OpenAI endpoint initialization paths. * 🧪 test: Add validateEndpointURL SSRF tests Covers unparseable URLs, localhost, private IPs, link-local/metadata, internal Docker/K8s hostnames, DNS resolution to private IPs, and legitimate public URLs. * 🛡️ fix: Add protocol enforcement and import order fix - Reject non-HTTP/HTTPS schemes (ftp://, file://, data:, etc.) in validateEndpointURL before SSRF hostname checks - Document DNS rebinding limitation and fail-open semantics in JSDoc - Fix import order in custom/initialize.ts per project conventions * 🧪 test: Expand SSRF validation coverage and add initializer integration tests Unit tests for validateEndpointURL: - Non-HTTP/HTTPS schemes (ftp, file, data) - IPv6 loopback, link-local, and unique-local addresses - .local and .internal TLD hostnames - DNS fail-open path (lookup failure allows request) Integration tests for initializeCustom and initializeOpenAI: - Guard fires when userProvidesURL is true - Guard skipped when URL is system-defined or falsy - SSRF rejection propagates and prevents getOpenAIConfig call * 🐛 fix: Correct broken env restore in OpenAI initialize spec process.env was captured by reference, not by value, making the restore closure a no-op. Snapshot individual env keys before mutation so they can be properly restored after each test. * 🛡️ fix: Throw structured ErrorTypes for SSRF base URL validation Replace plain-string Error throws in validateEndpointURL with JSON-structured errors using type 'invalid_base_url' (matching new ErrorTypes.INVALID_BASE_URL enum value). This ensures the client-side Error component can look up a localized message instead of falling through to the raw-text default. Changes across workspaces: - data-provider: add INVALID_BASE_URL to ErrorTypes enum - packages/api: throwInvalidBaseURL helper emits structured JSON - client: add errorMessages entry and localization key - tests: add structured JSON format assertion * 🧹 refactor: Use ErrorTypes enum key in Error.tsx for consistency Replace bare string literal 'invalid_base_url' with computed property [ErrorTypes.INVALID_BASE_URL] to match every other entry in the errorMessages map.	2026-03-15 18:41:59 -04:00
Danny Avila	7c39a45944	🐍 refactor: Normalize Non-Standard Browser MIME Type Aliases in inferMimeType (#12240) ... * 🐛 fix: Normalize non-standard browser MIME types in inferMimeType macOS Chrome/Firefox report .py files as text/x-python-script instead of text/x-python, causing client-side validation to reject Python file uploads. inferMimeType now normalizes known MIME type aliases before returning, so non-standard variants match the accepted regex patterns. * 🧪 test: Add tests for MIME type alias normalization in inferMimeType * 🐛 fix: Restore JSDoc params and make mimeTypeAliases immutable * 🧪 test: Add checkType integration tests, remove redundant DragDropModal tests	2026-03-14 22:43:18 -04:00
Danny Avila	71a3b48504	🔑 fix: Require OTP Verification for 2FA Re-Enrollment and Backup Code Regeneration (#12223) ... * fix: require OTP verification for 2FA re-enrollment and backup code regeneration * fix: require OTP verification for account deletion when 2FA is enabled * refactor: Improve code formatting and readability in TwoFactorController and UserController - Reformatted code in TwoFactorController and UserController for better readability by aligning parameters and breaking long lines. - Updated test cases in deleteUser.spec.js and TwoFactorController.spec.js to enhance clarity by formatting object parameters consistently. * refactor: Consolidate OTP and backup code verification logic in TwoFactorController and UserController - Introduced a new `verifyOTPOrBackupCode` function to streamline the verification process for TOTP tokens and backup codes across multiple controllers. - Updated the `enable2FA`, `disable2FA`, and `deleteUserController` methods to utilize the new verification function, enhancing code reusability and readability. - Adjusted related tests to reflect the changes in verification logic, ensuring consistent behavior across different scenarios. - Improved error handling and response messages for verification failures, providing clearer feedback to users. * chore: linting * refactor: Update BackupCodesItem component to enhance OTP verification logic - Consolidated OTP input handling by moving the 2FA verification UI logic to a more consistent location within the component. - Improved the state management for OTP readiness, ensuring the regenerate button is only enabled when the OTP is ready. - Cleaned up imports by removing redundant type imports, enhancing code clarity and maintainability. * chore: lint * fix: stage 2FA re-enrollment in pending fields to prevent disarmament window enable2FA now writes to pendingTotpSecret/pendingBackupCodes instead of overwriting the live fields. confirm2FA performs the atomic swap only after the new TOTP code is verified. If the user abandons mid-flow, their existing 2FA remains active and intact.	2026-03-14 01:51:31 -04:00
Danny Avila	f32907cd36	🔏 fix: MCP Server URL Schema Validation (#12204) ... * fix: MCP server configuration validation and schema - Added tests to reject URLs containing environment variable references for SSE, streamable-http, and websocket types in the MCP routes. - Introduced a new schema in the data provider to ensure user input URLs do not resolve environment variables, enhancing security against potential leaks. - Updated existing MCP server user input schema to utilize the new validation logic, ensuring consistent handling of user-supplied URLs across the application. * fix: MCP URL validation to reject env variable references - Updated tests to ensure that URLs for SSE, streamable-http, and websocket types containing environment variable patterns are rejected, improving security against potential leaks. - Refactored the MCP server user input schema to enforce stricter validation rules, preventing the resolution of environment variables in user-supplied URLs. - Introduced new test cases for various URL types to validate the rejection logic, ensuring consistent handling across the application. * test: Enhance MCPServerUserInputSchema tests for environment variable handling - Introduced new test cases to validate the prevention of environment variable exfiltration through user input URLs in the MCPServerUserInputSchema. - Updated existing tests to confirm that URLs containing environment variable patterns are correctly resolved or rejected, improving security against potential leaks. - Refactored test structure to better organize environment variable handling scenarios, ensuring comprehensive coverage of edge cases.	2026-03-12 23:19:31 -04:00
Danny Avila	cfbe812d63	✨ v0.8.3 (#12161) ... * ✨ v0.8.3 * chore: Bump package versions and update configuration - Updated package versions for @librechat/api (1.7.25), @librechat/client (0.4.54), librechat-data-provider (0.8.302), and @librechat/data-schemas (0.0.38). - Incremented configuration version in librechat.example.yaml to 1.3.6. * feat: Add OpenRouter headers to OpenAI configuration - Introduced 'X-OpenRouter-Title' and 'X-OpenRouter-Categories' headers in the OpenAI configuration for enhanced compatibility with OpenRouter services. - Updated related tests to ensure the new headers are correctly included in the configuration responses. * chore: Update package versions and dependencies - Bumped versions for several dependencies including @eslint/eslintrc to 3.3.4, axios to 1.13.5, express to 5.2.1, and lodash to 4.17.23. - Updated @librechat/backend and @librechat/frontend versions to 0.8.3. - Added new dependencies: turbo and mammoth. - Adjusted various other dependencies to their latest versions for improved compatibility and performance.	2026-03-09 15:19:57 -04:00
Danny Avila	2ac62a2e71	⛵ fix: Resolve Agent Provider Endpoint Type for File Upload Support (#12117) ... * chore: Remove unused setValueOnChange prop from MCPServerMenuItem component * fix: Resolve agent provider endpoint type for file upload support When using the agents endpoint with a custom provider (e.g., Moonshot), the endpointType was resolving to "agents" instead of the provider's actual type ("custom"), causing "Upload to Provider" to not appear in the file attach menu. Adds `resolveEndpointType` utility in data-provider that follows the chain: endpoint (if not agents) → agent.provider → agents. Applied consistently across AttachFileChat, DragDropContext, useDragHelpers, and AgentPanel file components (FileContext, FileSearch, Code/Files). * refactor: Extract useAgentFileConfig hook, restore deleted tests, fix review findings - Extract shared provider resolution logic into useAgentFileConfig hook (Finding #2: DRY violation across FileContext, FileSearch, Code/Files) - Restore 18 deleted test cases in AttachFileMenu.spec.tsx covering agent capabilities, SharePoint, edge cases, and button state (Finding #1: accidental test deletion) - Wrap fileConfigEndpoint in useMemo in AttachFileChat (Finding #3) - Fix misleading test name in AgentFileConfig.spec.tsx (Finding #4) - Fix import order in FileSearch.tsx, FileContext.tsx, Code/Files.tsx (Finding #5) - Add comment about cache gap in useDragHelpers (Finding #6) - Clarify resolveEndpointType JSDoc (Finding #7) * refactor: Memoize Footer component for performance optimization - Converted Footer component to a memoized version to prevent unnecessary re-renders. - Improved import structure by adding memo to the React import statement for clarity. * chore: Fix remaining review nits - Widen useAgentFileConfig return type to EModelEndpoint | string - Fix import order in FileContext.tsx and FileSearch.tsx - Remove dead endpointType param from setupMocks in AttachFileMenu test * fix: Pass resolved provider endpoint to file upload validation AgentPanel file components (FileContext, FileSearch, Code/Files) were hardcoding endpointOverride to "agents", causing both client-side validation (file limits, MIME types) and server-side validation to use the agents config instead of the provider-specific config. Adds endpointTypeOverride to UseFileHandling params so endpoint and endpointType can be set independently. Components now pass the resolved provider name and type from useAgentFileConfig, so the full fallback chain (provider → custom → agents → default) applies to file upload validation on both client and server. * test: Verify any custom endpoint is document-supported regardless of name Adds parameterized tests with arbitrary endpoint names (spaces, hyphens, colons, etc.) confirming that all custom endpoints resolve to document-supported through resolveEndpointType, both as direct endpoints and as agent providers. * fix: Use || for provider fallback, test endpointOverride wiring - Change providerValue ?? to providerValue || so empty string is treated as "no provider" consistently with resolveEndpointType - Add wiring tests to CodeFiles, FileContext, FileSearch verifying endpointOverride and endpointTypeOverride are passed correctly - Update endpointOverride JSDoc to document endpointType fallback	2026-03-07 10:45:43 -05:00
Danny Avila	a79f7cebd5	🤖 feat: GPT-5.4 and GPT-5.4-pro Context + Pricing (#12099) ... * ✨ feat: Add support for new GPT-5.4 and GPT-5.4-pro models - Introduced new token values and cache settings for 'gpt-5.4' and 'gpt-5.4-pro' in the API model configurations. - Updated maximum output limits for the new models in the tokens utility. - Included 'gpt-5.4' and 'gpt-5.4-pro' in the shared OpenAI models list for consistent access across the application. * 🔧 update: Enhance GPT-5.4 and GPT-5.4-pro model configurations - Refined token pricing and cache settings for 'gpt-5.4' and 'gpt-5.4-pro' in the API model configurations. - Added tests for cache multipliers and maximum token limits for the new models. - Updated shared OpenAI models list to include 'gpt-5.4-thinking' and added a note for verifying pricing before release. * 🔧 update: Add clarification to token pricing for 'gpt-5.4-pro' - Added a comment to the 'gpt-5.4-pro' model configuration in tokens.ts to specify that it shares the same token window as 'gpt-5.4', enhancing clarity for future reference.	2026-03-06 02:11:01 -05:00
Danny Avila	9956a72694	🧭 fix: Subdirectory Deployment Auth Redirect Path Doubling (#12077) ... * fix: subdirectory redirects * fix: use path-segment boundary check when stripping BASE_URL prefix A bare `startsWith(BASE_URL)` matches on character prefix, not path segments. With BASE_URL="/chat", a path like "/chatroom/c/abc" would incorrectly strip to "room/c/abc" (no leading slash). Guard with an exact-match-or-slash check: `p === BASE_URL || p.startsWith(BASE_URL + '/')`. Also removes the dead `BASE_URL !== '/'` guard — module init already converts '/' to ''. * test: add path-segment boundary tests and clarify subdirectory coverage - Add /chatroom, /chatbot, /app/chatroom regression tests to verify BASE_URL stripping only matches on segment boundaries - Clarify useAuthRedirect subdirectory test documents React Router basename behavior (BASE_URL stripping tested in api-endpoints-subdir) - Use `delete proc.browser` instead of undefined assignment for cleanup - Add rationale to eslint-disable comment for isolateModules require * fix: use relative path and correct instructions in subdirectory test script - Replace hardcoded /home/danny/LibreChat/.env with repo-root-relative path so the script works from any checkout location - Update instructions to use production build (npm run build && npm run backend) since nginx proxies to :3080 which only serves the SPA after a full build, not during frontend:dev on :3090 * fix: skip pointless redirect_to=/ for root path and fix jsdom 26+ compat buildLoginRedirectUrl now returns plain /login when the resolved path is root — redirect_to=/ adds no value since / immediately redirects to /c/new after login anyway. Also rewrites api-endpoints.spec.ts to use window.history.replaceState instead of Object.defineProperty(window, 'location', ...) which jsdom 26+ no longer allows. * test: fix request-interceptor.spec.ts for jsdom 26+ compatibility Switch from jsdom to happy-dom environment which allows Object.defineProperty on window.location. jsdom 26+ made location non-configurable, breaking all 8 tests in this file. * chore: update browser property handling in api-endpoints-subdir test Changed the handling of the `proc.browser` property from deletion to setting it to false, ensuring compatibility with the current testing environment. * chore: update backend restart instructions in test subdirectory setup script Changed the instruction for restarting the backend from "npm run backend:dev" to "npm run backend" to reflect the correct command for the current setup. * refactor: ensure proper cleanup in loadModuleWithBase function Wrapped the module loading logic in a try-finally block to guarantee that the `proc.browser` property is reset to false and the base element is removed, improving reliability in the testing environment. * refactor: improve browser property handling in loadModuleWithBase function Revised the management of the `proc.browser` property to store the original value before modification, ensuring it is restored correctly after module loading. This enhances the reliability of the testing environment.	2026-03-05 01:38:44 -05:00
Danny Avila	7e85cf71bd	✨ v0.8.3-rc2 (#12027)	2026-03-04 09:28:20 -05:00
Danny Avila	a2a09b556a	🤖 feat: gemini-3.1-flash-lite-preview Window & Pricing (#12043) ... * 🤖 feat: `gemini-3.1-flash-lite-preview` Window & Pricing - Updated `.env.example` to include `gemini-3.1-flash-lite-preview` in the list of available models. - Enhanced `tx.js` to define token values for `gemini-3.1-flash-lite`. - Adjusted `tokens.ts` to allocate input tokens for `gemini-3.1-flash-lite`. - Modified `config.ts` to include `gemini-3.1-flash-lite-preview` in the default models list. * chore: testing for `gemini-3.1-flash-lite` model, comments - Updated `tx.js` to include cache token values for `gemini-3.1-flash-lite` with specific write and read rates. - Enhanced `tx.spec.js` to include tests for the new `gemini-3.1-flash-lite-preview` model, ensuring correct rate retrieval for both prompt and completion token types.	2026-03-03 13:47:16 -05:00
Danny Avila	619d35360d	🔒 fix: Request interceptor for Shared Link Page Scenarios (#12036) ... * ♻️ refactor: Centralize `buildLoginRedirectUrl` in data-provider Move `buildLoginRedirectUrl` from `client/src/utils/redirect.ts` into `packages/data-provider/src/api-endpoints.ts` so the axios 401 interceptor (and any other data-provider consumer) can use the canonical implementation with the LOGIN_PATH_RE guard and BASE_URL awareness. The client module now re-exports from `librechat-data-provider`, keeping all existing imports working unchanged. * 🔒 fix: Shared link 401 interceptor bypass and redirect loop (#12033) Fixes three issues in the axios 401 response interceptor that prevented private shared links (ALLOW_SHARED_LINKS_PUBLIC=false) from working: 1. `window.location.href.includes('share/')` matched the full URL (including query params and hash), causing false positives. Changed to `window.location.pathname.startsWith('/share/')`. 2. When token refresh returned no token on a share page, the interceptor logged and fell through without redirecting, causing an infinite retry loop via React Query. Now redirects to login using `buildLoginRedirectUrl()` which preserves the share URL for post-login navigation. 3. `processQueue` was never called in the no-token branch, leaving queued requests with dangling promise callbacks. Added `processQueue(error, null)` before the redirect. * ✅ test: Comprehensive 401 interceptor tests for shared link auth flow Rewrite interceptor test suite to cover all shared link auth scenarios: - Unauthenticated user on share page with failed refresh → redirect - Authenticated user on share page with failed refresh → redirect - share/ in query params does NOT bypass the auth header guard - Login path guard: redirect to plain /login (no redirect_to loop) - Refresh success: assert exact call count (toBe(3) vs toBeGreaterThan) Test reliability improvements: - window.location teardown moved to afterEach (no state leak on failure) - expect.assertions(N) on all tests (catch silent false passes) - Shared setWindowLocation helper for consistent location mocking * ♻️ refactor: Import `buildLoginRedirectUrl` directly from data-provider Update `AuthContext.tsx` and `useAuthRedirect.ts` to import `buildLoginRedirectUrl` from `librechat-data-provider` instead of re-exporting through `~/utils/redirect.ts`. Convert `redirect.ts` to ESM-style inline exports and remove the re-export of `buildLoginRedirectUrl`. * ✅ test: Move `buildLoginRedirectUrl` tests to data-provider Tests for `buildLoginRedirectUrl` now live alongside the implementation in `packages/data-provider/specs/api-endpoints.spec.ts`. Removed the duplicate describe block from the client redirect test file since it no longer owns that function.	2026-03-03 12:03:33 -05:00
Danny Avila	b18915a96b	🚪 fix: Complete OIDC RP-Initiated Logout With id_token_hint and Redirect Race Fix (#12024) ... * fix: complete OIDC logout implementation The OIDC logout feature added in #5626 was incomplete: 1. Backend: Missing id_token_hint/client_id parameters required by the RP-Initiated Logout spec. Keycloak 18+ rejects logout without these. 2. Frontend: The logout redirect URL was passed through isSafeRedirect() which rejects all absolute URLs. The redirect was silently dropped. Backend: Add id_token_hint (preferred) or client_id (fallback) to the logout URL for OIDC spec compliance. Frontend: Use window.location.replace() for logout redirects from the backend, bypassing isSafeRedirect() which was designed for user-input validation. Fixes #5506 * fix: accept undefined in setTokenHeader to properly clear Authorization header When token is undefined, delete the Authorization header instead of setting it to "Bearer undefined". Removes the @ts-ignore workaround in AuthContext. * fix: skip axios 401 refresh when Authorization header is cleared When the Authorization header has been removed (e.g. during logout), the response interceptor now skips the token refresh flow. This prevents a successful refresh from canceling an in-progress OIDC external redirect via window.location.replace(). * fix: guard against undefined OPENID_CLIENT_ID in logout URL Prevent literal "client_id=undefined" in the OIDC end-session URL when OPENID_CLIENT_ID is not set. Log a warning when neither id_token_hint nor client_id is available. * fix: prevent race condition canceling OIDC logout redirect The logout mutation wrapper's cleanup (clearStates, removeQueries) triggers re-renders and 401s on in-flight requests. The axios interceptor would refresh the token successfully, firing dispatchTokenUpdatedEvent which cancels the window.location.replace() navigation to the IdP's end_session_endpoint. Fix: - Clear Authorization header synchronously before redirect so the axios interceptor skips refresh for post-logout 401s - Add isExternalRedirectRef to suppress silentRefresh and useEffect side effects during the redirect - Add JSDoc explaining why isSafeRedirect is bypassed * test: add LogoutController and AuthContext logout test coverage LogoutController.spec.js (13 tests): - id_token_hint from session and cookie fallback - client_id fallback, including undefined OPENID_CLIENT_ID guard - Disabled endpoint, missing issuer, non-OpenID user - post_logout_redirect_uri (custom and default) - Missing OpenID config and end_session_endpoint - Error handling and cookie clearing AuthContext.spec.tsx (3 tests): - OIDC redirect calls window.location.replace + setTokenHeader - Non-redirect logout path - Logout error handling * test: add coverage for setTokenHeader, axios interceptor guard, and silentRefresh suppression headers-helpers.spec.ts (3 tests): - Sets Authorization header with Bearer token - Deletes Authorization header when called with undefined - No-op when clearing an already absent header request-interceptor.spec.ts (2 tests): - Skips refresh when Authorization header is cleared (the race fix) - Attempts refresh when Authorization header is present AuthContext.spec.tsx (1 new test): - Verifies silentRefresh is not triggered after OIDC redirect * test: enhance request-interceptor tests with adapter restoration and refresh verification - Store the original axios adapter before tests and restore it after all tests to prevent side effects. - Add verification for the refresh endpoint call in the interceptor tests to ensure correct behavior during token refresh attempts. * test: enhance AuthContext tests with live rendering and improved logout error handling - Introduced a new `renderProviderLive` function to facilitate testing with silentRefresh. - Updated tests to use the live rendering function, ensuring accurate simulation of authentication behavior. - Enhanced logout error handling test to verify that auth state is cleared without external redirects. * test: update LogoutController tests for OpenID config error handling - Renamed test suite to clarify that it handles cases when OpenID config is not available. - Modified test to check for error thrown by getOpenIdConfig instead of returning null, ensuring proper logging of the error message. * refactor: improve OpenID config error handling in LogoutController - Simplified error handling for OpenID configuration retrieval by using a try-catch block. - Updated logging to provide clearer messages when the OpenID config is unavailable. - Ensured that the end session endpoint is only accessed if the OpenID config is successfully retrieved. --------- Co-authored-by: cloudspinner <stijn.tastenhoye@gmail.com>	2026-03-02 21:34:13 -05:00
Danny Avila	2a5123bfa1	📅 refactor: Replace Numeric Weekday Index with Named Day in Date Template Variables (#12022) ... * feat(data-provider): include timezone and weekday label in current_datetime * fix(data-provider): use named weekday for both date variables and single dayjs instance Use a single `const now = dayjs()` instead of 5 separate instantiations, apply named weekday to `{{current_date}}` (not just `{{current_datetime}}`), simplify weekday format from `(weekday=Monday)` to `(Monday)`, and harden test mock fallback to throw on unhandled format strings. * chore(data-provider): remove dead day() mock from parsers spec --------- Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com>	2026-03-02 19:22:11 -05:00
Danny Avila	723acd830c	🎚️ feat: Add Thinking Level Parameter for Gemini 3+ Models (#11994) ... * 🧠 feat: Add Thinking Level Config for Gemini 3 Models - Introduced a new setting for 'thinking level' in the Google configuration, allowing users to control the depth of reasoning for Gemini 3 models. - Updated translation files to include the new 'thinking level' label and description. - Enhanced the Google LLM configuration to support the new 'thinking level' parameter, ensuring compatibility with both Google and Vertex AI providers. - Added necessary schema and type definitions to accommodate the new setting across the data provider and API layers. * test: Google LLM Configuration for Gemini 3 Models - Added tests to validate default thinking configuration for Gemini 3 models, ensuring `thinkingConfig` is set correctly without `thinkingLevel`. - Implemented logic to ignore `thinkingBudget` for Gemini 3+ models, confirming that it does not affect the configuration. - Included a test to verify that `gemini-2.9-flash` is not classified as a Gemini 3+ model, maintaining expected behavior for earlier versions. - Updated existing tests to ensure comprehensive coverage of the new configurations and behaviors. * fix: Update translation for Google LLM thinking settings - Revised descriptions for 'thinking budget' and 'thinking level' in the English translation file to clarify their applicability to different Gemini model versions. - Ensured that the new descriptions accurately reflect the functionality and usage of the settings for Gemini 2.5 and 3 models. * docs: Update comments for Gemini 3+ thinking configuration - Added detailed comments in the Google LLM configuration to clarify the differences between `thinkingLevel` and `thinkingBudget` for Gemini 3+ models. - Explained the necessity of `includeThoughts` in Vertex AI requests and how it interacts with `thinkingConfig` for improved understanding of the configuration logic. * fix: Update comment for Gemini 3 model versioning - Corrected comment in the configuration file to reflect the proper versioning for Gemini models, changing "Gemini 3.0 Models" to "Gemini 3 Models" for clarity and consistency. * fix: Update thinkingLevel schema for Gemini 3 Models - Removed nullable option from the thinkingLevel field in the tConversationSchema to ensure it is always defined when present, aligning with the intended configuration for Gemini 3 models.	2026-02-28 16:56:10 -05:00
Danny Avila	e6b324b259	🧠 feat: Add reasoning_effort configuration for Bedrock models (#11991) ... * 🧠 feat: Add reasoning_effort configuration for Bedrock models - Introduced a new `reasoning_effort` setting in the Bedrock configuration, allowing users to specify the reasoning level for supported models. - Updated the input parser to map `reasoning_effort` to `reasoning_config` for Moonshot and ZAI models, ensuring proper handling of reasoning levels. - Enhanced tests to validate the mapping of `reasoning_effort` to `reasoning_config` and to ensure correct behavior for various model types, including Anthropic models. - Updated translation files to include descriptions for the new configuration option. * chore: Update translation keys for Bedrock reasoning configuration - Renamed translation key from `com_endpoint_bedrock_reasoning_config` to `com_endpoint_bedrock_reasoning_effort` for consistency with the new configuration setting. - Updated the parameter settings to reflect the change in the description key, ensuring accurate mapping in the application. * 🧪 test: Enhance bedrockInputParser tests for reasoning_config handling - Added tests to ensure that stale `reasoning_config` is stripped when switching models from Moonshot to Meta and ZAI to DeepSeek. - Included additional tests to verify that `reasoning_effort` values of "none", "minimal", and "xhigh" do not forward to `reasoning_config` for Moonshot and ZAI models. - Improved coverage for the bedrockInputParser functionality to ensure correct behavior across various model configurations. * feat: Introduce Bedrock reasoning configuration and update input parser - Added a new `BedrockReasoningConfig` enum to define reasoning levels: low, medium, and high. - Updated the `bedrockInputParser` to utilize the new reasoning configuration, ensuring proper handling of `reasoning_effort` values. - Enhanced logic to validate `reasoning_effort` against the defined configuration values before assigning to `reasoning_config`. - Improved code clarity with additional comments and refactored conditions for better readability.	2026-02-28 15:02:09 -05:00
Danny Avila	046e92217f	🧩 feat: OpenDocument Format File Upload and Native ODS Parsing (#11959) ... * ✨ feat: Add support for OpenDocument MIME types in file configuration Updated the applicationMimeTypes regex to include support for OASIS OpenDocument formats, enhancing the file type recognition capabilities of the data provider. * feat: document processing with OpenDocument support Added support for OpenDocument Spreadsheet (ODS) MIME type in the file processing service and updated the document parser to handle ODS files. Included tests to verify correct parsing of ODS documents and updated file configuration to recognize OpenDocument formats. * refactor: Enhance document processing to support additional Excel MIME types Updated the document processing logic to utilize a regex for matching Excel MIME types, improving flexibility in handling various Excel file formats. Added tests to ensure correct parsing of new MIME types, including multiple Excel variants and OpenDocument formats. Adjusted file configuration to include these MIME types for better recognition in the file processing service. * feat: Add support for additional OpenDocument MIME types in file processing Enhanced the document processing service to support ODT, ODP, and ODG MIME types. Updated tests to verify correct routing through the OCR strategy for these new formats. Adjusted documentation to reflect changes in handled MIME types for improved clarity.	2026-02-26 14:39:49 -05:00
Danny Avila	9a8a5d66d7	⏱️ fix: Separate MCP GET SSE Stream Timeout from POST and Suppress SDK-Internal Recovery Errors (#11936) ... * fix: Separate MCP GET SSE body timeout from POST and suppress SDK-internal stream recovery - Add a dedicated GET Agent with a configurable `sseReadTimeout` (default 5 min, matching the Python MCP SDK) so idle SSE streams time out independently of POST requests, preventing the reconnect-loop log flood described in Discussion #11230. - Suppress "SSE stream disconnected" and "Failed to reconnect SSE stream" errors in setupTransportErrorHandlers — these are SDK-internal recovery events, not transport failures. "Maximum reconnection attempts exceeded" still escalates. - Add optional `sseReadTimeout` to BaseOptionsSchema for per-server configuration. - Add 6 tests: agent timeout separation, custom sseReadTimeout, SSE disconnect suppression (3 unit), and a real-server integration test proving the GET stream recovers without a full transport rebuild. * fix: Refactor MCP connection timeouts and error handling - Updated the `DEFAULT_SSE_READ_TIMEOUT` to use a constant for better readability. - Introduced internal error message constants for SSE stream disconnection and reconnection failures to improve maintainability. - Enhanced type safety in tests by ensuring the options symbol is defined before usage. - Updated the `sseReadTimeout` in `BaseOptionsSchema` to enforce positive values, ensuring valid configurations. * chore: Update SSE read timeout documentation format in BaseOptionsSchema - Changed the default timeout value comment in BaseOptionsSchema to use an underscore for better readability, aligning with common formatting practices.	2026-02-24 21:05:58 -05:00
Danny Avila	f3eb197675	💎 fix: Gemini Image Gen Tool Vertex AI Auth and File Storage (#11923) ... * chore: saveToCloudStorage function and enhance error handling - Removed unnecessary parameters and streamlined the logic for saving images to cloud storage. - Introduced buffer handling for base64 image data and improved the integration with file strategy functions. - Enhanced error handling during local image saving to ensure robustness. - Updated the createGeminiImageTool function to reflect changes in the saveToCloudStorage implementation. * refactor: streamline image persistence logic in GeminiImageGen - Consolidated image saving functionality by renaming and refactoring the saveToCloudStorage function to persistGeneratedImage. - Improved error handling and logging for image persistence operations. - Enhanced the replaceUnwantedChars function to better sanitize input strings. - Updated createGeminiImageTool to reflect changes in image handling and ensure consistent behavior across storage strategies. * fix: clean up GeminiImageGen by removing unused functions and improving logging - Removed the getSafeFormat and persistGeneratedImage functions to streamline image handling. - Updated logging in createGeminiImageTool for clarity and consistency. - Consolidated imports by eliminating unused dependencies, enhancing code maintainability. * chore: update environment configuration and manifest for unused GEMINI_VERTEX_ENABLED - Removed the Vertex AI configuration option from .env.example to simplify setup. - Updated the manifest.json to reflect the removal of the Vertex AI dependency in the authentication field. - Cleaned up the createGeminiImageTool function by eliminating unused fields related to Vertex AI, streamlining the code. * fix: update loadAuthValues call in loadTools function for GeminiImageGen tool - Modified the loadAuthValues function call to include throwError: false, preventing exceptions on authentication failures. - Removed the unused processFileURL parameter from the tool context object, streamlining the code. * refactor: streamline GoogleGenAI initialization in GeminiImageGen - Removed unused file system access check for Google application credentials, simplifying the environment setup. - Added googleAuthOptions to the GoogleGenAI instantiation, enhancing the configuration for authentication. * fix: update Gemini API Key label and description in manifest.json - Changed the label to indicate that the Gemini API Key is optional. - Revised the description to clarify usage with Vertex AI and service accounts, enhancing user guidance. * fix: enhance abort signal handling in createGeminiImageTool - Introduced derivedSignal to manage abort events during image generation, improving responsiveness to cancellation requests. - Added an abortHandler to log when image generation is aborted, enhancing debugging capabilities. - Ensured proper cleanup of event listeners in the finally block to prevent memory leaks. * fix: update authentication handling for plugins to support optional fields - Added support for optional authentication fields in the manifest and PluginAuthForm. - Updated the checkPluginAuth function to correctly validate plugins with optional fields. - Enhanced tests to cover scenarios with optional authentication fields, ensuring accurate validation logic.	2026-02-24 08:21:02 -05:00
Dustin Healy	1d0a4c501f	🪨 feat: AWS Bedrock Document Uploads (#11912) ... * feat: add aws bedrock upload to provider support * chore: address copilot comments * feat: add shared Bedrock document format types and MIME mapping Bedrock Converse API accepts 9 document formats beyond PDF. Add BedrockDocumentFormat union type, MIME-to-format mapping, and helpers in data-provider so both client and backend can reference them. * refactor: generalize Bedrock PDF validation to support all document types Rename validateBedrockPdf to validateBedrockDocument with MIME-aware logic: 4.5MB hard limit applies to all types, PDF header check only runs for application/pdf. Adds test coverage for non-PDF documents. * feat: support all Bedrock document formats in encoding pipeline Widen file type gates to accept csv, doc, docx, xls, xlsx, html, txt, md for Bedrock. Uses shared MIME-to-format map instead of hardcoded 'pdf'. Other providers' PDF-only paths remain unchanged. * feat: expand Bedrock file upload UI to accept all document types Add 'image_document_extended' upload type for Bedrock with accept filters for all 9 supported formats. Update drag-and-drop validation to use isBedrockDocumentType helper. * fix: route Bedrock document types through provider pipeline	2026-02-23 22:32:44 -05:00
Danny Avila	7ce898d6a0	📄 feat: Local Text Extraction for PDF, DOCX, and XLS/XLSX (#11900) ... * feat: Added "document parser" OCR strategy The document parser uses libraries to parse the text out of known document types. This lets LibreChat handle some complex document types without having to use a secondary service (like Mistral or standing up a RAG API server). To enable the document parser, set the ocr strategy to "document_parser" in librechat.yaml. We now support: - PDFs using pdfjs - DOCX using mammoth - XLS/XLSX using SheetJS (The associated packages were also added to the project.) * fix: applied Copilot code review suggestions - Properly calculate length of text based on UTF8. - Avoid issues with loading / blocking PDF parsing. * fix: improved docs on parseDocument() * chore: move to packages/api for TS support * refactor: make document processing the default ocr strategy - Introduced support for additional document types in the OCR strategy, including PDF, DOCX, and XLS/XLSX. - Updated the file upload handling to dynamically select the appropriate parsing strategy based on the file type. - Refactored the document parsing functions to use asynchronous imports for improved performance and maintainability. * test: add unit tests for processAgentFileUpload functionality - Introduced a new test suite for the processAgentFileUpload function in process.spec.js. - Implemented various test cases to validate OCR strategy selection based on file types, including PDF, DOCX, XLSX, and XLS. - Mocked dependencies to ensure isolated testing of file upload handling and strategy selection logic. - Enhanced coverage for scenarios involving OCR capability checks and default strategy fallbacks. * chore: update pdfjs-dist version and enhance document parsing tests - Bumped pdfjs-dist dependency to version 5.4.624 in both api and packages/api. - Refactored document parsing tests to use 'originalname' instead of 'filename' for file objects. - Added a new test case for parsing XLS files to improve coverage of document types supported by the parser. - Introduced a sample XLS file for testing purposes. * feat: enforce text size limit and improve OCR fallback handling in processAgentFileUpload - Added a check to ensure extracted text does not exceed the 15MB storage limit, throwing an error if it does. - Refactored the OCR handling logic to improve fallback behavior when the configured OCR fails, ensuring a more robust document processing flow. - Enhanced unit tests to cover scenarios for oversized text and fallback mechanisms, ensuring proper error handling and functionality. * fix: correct OCR URL construction in performOCR function - Updated the OCR URL construction to ensure it correctly appends '/ocr' to the base URL if not already present, improving the reliability of the OCR request. --------- Co-authored-by: Dan Lew <daniel@mightyacorn.com>	2026-02-22 14:22:45 -05:00
Danny Avila	7a1d2969b8	🤖 feat: Gemini 3.1 Pricing and Context Window (#11884) ... - Added support for the new Gemini 3.1 models, including 'gemini-3.1-pro-preview' and 'gemini-3.1-pro-preview-customtools'. - Updated pricing logic to apply standard and premium rates based on token usage thresholds for the new models. - Enhanced tests to validate pricing behavior for both standard and premium scenarios. - Modified configuration files to include Gemini 3.1 models in the default model lists and token value mappings. - Updated environment example file to reflect the new model options.	2026-02-20 16:21:32 -05:00
Danny Avila	9eeec6bc4f	✨ v0.8.3-rc1 (#11856) ... * 🔧 chore: Update configuration version to 1.3.4 in librechat.example.yaml and data-provider config.ts - Bumped the configuration version in both librechat.example.yaml and data-provider/src/config.ts to 1.3.4. - Added new options for creating prompts and agents in the interface section of the YAML configuration. - Updated capabilities list in the endpoints section to include 'deferred_tools'. * 🔧 chore: Bump version to 0.8.3-rc1 across multiple packages and update related configurations - Updated version to 0.8.3-rc1 in bun.lock, package.json, and various package.json files for frontend, backend, and data provider. - Adjusted Dockerfile and Dockerfile.multi to reflect the new version. - Incremented version for @librechat/api from 1.7.22 to 1.7.23 and for @librechat/client from 0.4.51 to 0.4.52. - Updated appVersion in helm Chart.yaml to 0.8.3-rc1. - Enhanced test configuration to align with the new version. * 🔧 chore: Update version to 0.8.300 across multiple packages - Bumped version to 0.8.300 in bun.lock, package-lock.json, and package.json for the data provider. - Ensured consistency in versioning across the frontend, backend, and data provider packages. * 🔧 chore: Bump package versions in bun.lock - Updated version for @librechat/api from 1.7.22 to 1.7.23. - Incremented version for @librechat/client from 0.4.51 to 0.4.52. - Bumped version for @librechat/data-schemas from 0.0.35 to 0.0.36.	2026-02-18 20:36:03 -05:00
Danny Avila	0697e8cd60	🤖 feat: Claude Sonnet 4.6 support (#11829) ... * 🤖 feat: Claude Sonnet 4.6 support - Updated .env.example to include claude-sonnet-4-6 in the list of available models. - Enhanced token value assignments in api/models/tx.js and packages/api/src/utils/tokens.ts to accommodate claude-sonnet-4-6. - Added tests in packages/data-provider/specs/bedrock.spec.ts to verify support for claude-sonnet-4-6 in adaptive thinking and context-1m functionalities. - Modified bedrock.ts to correctly parse and identify the version of claude-sonnet-4-6 for adaptive thinking checks. - Included claude-sonnet-4-6 in sharedAnthropicModels and bedrockModels for consistent model availability. * chore: additional Claude Sonnet 4.6 tests - Added unit tests for Claude Sonnet 4.6 in `tokens.spec.js` to verify context length and max output tokens. - Updated `helpers.ts` documentation to reflect adaptive thinking support for Sonnet 4.6. - Enhanced `llm.spec.ts` with tests for context headers and adaptive thinking configurations for Claude Sonnet 4.6. - Improved `bedrock.spec.ts` to ensure correct parsing and handling of Claude Sonnet 4.6 model variations with adaptive thinking.	2026-02-17 15:24:03 -05:00
Danny Avila	12f45c76ee	🎮 feat: Bedrock Parameters for OpenAI GPT-OSS models (#11798) ... Add OpenAI as a Bedrock provider so that selecting openai.gpt-oss-* models in the Bedrock agent UI renders the general parameter settings (temperature, top_p, max_tokens) instead of a blank panel. Also add token context lengths (128K) for gpt-oss-20b and gpt-oss-120b.	2026-02-14 14:10:32 -05:00
Danny Avila	10685fca9f	🗂️ refactor: Artifacts via Model Specs & Scope Badge Persistence by Spec Context (#11796) ... * 🔧 refactor: Simplify MCP selection logic in useMCPSelect hook - Removed redundant useEffect for setting ephemeral agent when MCP values change. - Integrated ephemeral agent update directly into the MCP value change handler, improving code clarity and reducing unnecessary re-renders. - Updated dependencies in the effect hook to ensure proper state management. Why Effect 2 Was Added (PR #9528) PR #9528 was a refactor that migrated MCP state from useLocalStorage hooks to Jotai atomWithStorage. Before that PR, useLocalStorage handled bidirectional sync between localStorage and Recoil in one abstraction. After the migration, the two useEffect hooks were introduced to bridge Jotai ↔ Recoil: - Effect 1 (Recoil → Jotai): When ephemeralAgent.mcp changes externally, update the Jotai atom (which drives the UI dropdown) - Effect 2 (Jotai → Recoil): When mcpValues changes, push it back to ephemeralAgent.mcp (which is read at submission time) Effect 2 was needed because in that PR's design, setMCPValues only wrote to Jotai — it never touched Recoil. Effect 2 was the bridge to propagate user selections into the ephemeral agent. Why Removing It Is Correct All user-initiated MCP changes go through setMCPValues. The callers are in useMCPServerManager: toggleServerSelection, batchToggleServers, OAuth success callbacks, and access revocation. Our change puts the Recoil write directly in that callback, so all these paths are covered. All external changes go through Recoil, handled by Effect 1 (kept). Model spec application (applyModelSpecEphemeralAgent), agent template application after submission, and BadgeRowContext initialization all write directly to ephemeralAgentByConvoId. Effect 1 watches ephemeralAgent?.mcp and syncs those into the Jotai atom for the UI. There is no code path where mcpValues changes without going through setMCPValues or Effect 1. The only other source is atomWithStorage's getOnInit reading from localStorage on mount — that's just restoring persisted state and is harmless (overwritten by Effect 1 if the ephemeral agent has values). Additional Benefits - Eliminates the race condition. Effect 2 fired on mount with Jotai's stale default ([]), overwriting ephemeralAgent.mcp that had been set by a model spec. Our change prevents that because the imperative sync only fires on explicit user action. - Eliminates infinite loop risk. The old bidirectional two-effect approach relied on isEqual/JSON.stringify checks to break cycles. The new unidirectional-reactive (Effect 1) + imperative (setMCPValues) approach has no such risk. - Effect 1's enhancements are preserved. The mcp_clear sentinel handling and configuredServers filtering (both added after PR #9528) continue to work correctly. * ✨ feat: Add artifacts support to model specifications and ephemeral agents - Introduced `artifacts` property in the model specification and ephemeral agent types, allowing for string or boolean values. - Updated `applyModelSpecEphemeralAgent` to handle artifacts, defaulting to 'default' if true or an empty string if not specified. - Enhanced localStorage handling to store artifacts alongside other agent properties, improving state management for ephemeral agents. * 🔧 refactor: Update BadgeRowContext to improve localStorage handling - Modified the logic to only apply values from localStorage that were actually stored, preventing unnecessary overrides of the ephemeral agent. - Simplified the setting of ephemeral agent values by directly using initialValues, enhancing code clarity and maintainability. * 🔧 refactor: Enhance ephemeral agent handling in BadgeRowContext and model spec application - Updated BadgeRowContext to apply localStorage values only for tools not already set in ephemeralAgent, improving state management. - Modified useApplyModelSpecEffects to reset the ephemeral agent when no spec is provided but specs are configured, ensuring localStorage defaults are applied correctly. - Streamlined the logic for applying model spec properties, enhancing clarity and maintainability. * refactor: Isolate spec and non-spec tool/MCP state with environment-keyed storage Spec tool state (badges, MCP) and non-spec user preferences previously shared conversation-keyed localStorage, causing cross-pollination when switching between spec and non-spec models. This introduces environment-keyed storage so each context maintains independent persisted state. Key changes: - Spec active: no localStorage persistence — admin config always applied fresh - Non-spec (with specs configured): tool/MCP state persisted to __defaults__ key - No specs configured: zero behavior change (conversation-keyed storage) - Per-conversation isolation preserved for existing conversations - Dual-write on user interaction updates both conversation and environment keys - Remove mcp_clear sentinel in favor of null ephemeral agent reset * refactor: Enhance ephemeral agent initialization and MCP handling in BadgeRowContext and useMCPSelect - Updated BadgeRowContext to clarify the handling of localStorage values for ephemeral agents, ensuring proper initialization based on conversation state. - Improved useMCPSelect tests to accurately reflect behavior when setting empty MCP values, ensuring the visual selection clears as expected. - Introduced environment-keyed storage logic to maintain independent state for spec and non-spec contexts, enhancing user experience during context switching. * test: Add comprehensive tests for useToolToggle and applyModelSpecEphemeralAgent hooks - Introduced unit tests for the useToolToggle hook, covering dual-write behavior in non-spec mode and per-conversation isolation. - Added tests for applyModelSpecEphemeralAgent, ensuring correct application of model specifications and user overrides from localStorage. - Enhanced test coverage for ephemeral agent state management during conversation transitions, validating expected behaviors for both new and existing conversations.	2026-02-14 13:56:50 -05:00
Danny Avila	467df0f07a	🎭 feat: Override Custom Endpoint Schema with Specified Params Endpoint (#11788) ... * 🔧 refactor: Simplify payload parsing and enhance getSaveOptions logic - Removed unused bedrockInputSchema from payloadParser, streamlining the function. - Updated payloadParser to handle optional chaining for model parameters. - Enhanced getSaveOptions to ensure runOptions defaults to an empty object if parsing fails, improving robustness. - Adjusted the assignment of maxContextTokens to use the instance variable for consistency. * 🔧 fix: Update maxContextTokens assignment logic in initializeAgent function - Enhanced the maxContextTokens assignment to allow for user-defined values, ensuring it defaults to a calculated value only when not provided or invalid. This change improves flexibility in agent initialization. * 🧪 test: Add unit tests for initializeAgent function - Introduced comprehensive unit tests for the initializeAgent function, focusing on maxContextTokens behavior. - Tests cover scenarios for user-defined values, fallback calculations, and edge cases such as zero and negative values, enhancing overall test coverage and reliability of agent initialization logic. * refactor: default params Endpoint Configuration Handling - Integrated `getEndpointsConfig` to fetch endpoint configurations, allowing for dynamic handling of `defaultParamsEndpoint`. - Updated `buildEndpointOption` to pass `defaultParamsEndpoint` to `parseCompactConvo`, ensuring correct parameter handling based on endpoint type. - Added comprehensive unit tests for `buildDefaultConvo` and `cleanupPreset` to validate behavior with `defaultParamsEndpoint`, covering various scenarios and edge cases. - Refactored related hooks and utility functions to support the new configuration structure, improving overall flexibility and maintainability. * refactor: Centralize defaultParamsEndpoint retrieval - Introduced `getDefaultParamsEndpoint` function to streamline the retrieval of `defaultParamsEndpoint` across various hooks and middleware. - Updated multiple files to utilize the new function, enhancing code consistency and maintainability. - Removed redundant logic for fetching `defaultParamsEndpoint`, simplifying the codebase.	2026-02-13 23:04:51 -05:00
Danny Avila	276ac8d011	🛰️ feat: Add Bedrock Parameter Settings for MoonshotAI and Z.AI Models (#11783) ... - Introduced new model entries for 'moonshotai.kimi' and 'moonshotai.kimi-k2.5' in tokens.ts. - Updated parameterSettings.ts to include configurations for MoonshotAI and ZAI providers. - Enhanced schemas.ts by adding MoonshotAI and ZAI to the BedrockProviders enum for better integration.	2026-02-13 11:21:53 -05:00
Danny Avila	599f4a11f1	🛡️ fix: Secure MCP/Actions OAuth Flows, Resolve Race Condition & Tool Cache Cleanup (#11756) ... * 🔧 fix: Update OAuth error message for clarity - Changed the default error message in the OAuth error route from 'Unknown error' to 'Unknown OAuth error' to provide clearer context during authentication failures. * 🔒 feat: Enhance OAuth flow with CSRF protection and session management - Implemented CSRF protection for OAuth flows by introducing `generateOAuthCsrfToken`, `setOAuthCsrfCookie`, and `validateOAuthCsrf` functions. - Added session management for OAuth with `setOAuthSession` and `validateOAuthSession` middleware. - Updated routes to bind CSRF tokens for MCP and action OAuth flows, ensuring secure authentication. - Enhanced tests to validate CSRF handling and session management in OAuth processes. * 🔧 refactor: Invalidate cached tools after user plugin disconnection - Added a call to `invalidateCachedTools` in the `updateUserPluginsController` to ensure that cached tools are refreshed when a user disconnects from an MCP server after a plugin authentication update. This change improves the accuracy of tool data for users. * chore: imports order * fix: domain separator regex usage in ToolService - Moved the declaration of `domainSeparatorRegex` to avoid redundancy in the `loadActionToolsForExecution` function, improving code clarity and performance. * chore: OAuth flow error handling and CSRF token generation - Enhanced the OAuth callback route to validate the flow ID format, ensuring proper error handling for invalid states. - Updated the CSRF token generation function to require a JWT secret, throwing an error if not provided, which improves security and clarity in token generation. - Adjusted tests to reflect changes in flow ID handling and ensure robust validation across various scenarios.	2026-02-12 14:22:05 -05:00
Danny Avila	5b67e48fe1	🗃️ refactor: Separate Tool Cache Namespace for Blue/Green Deployments (#11738) ... * 🔧 refactor: Introduce TOOL_CACHE for isolated caching of tools - Added TOOL_CACHE key to CacheKeys enum for managing tool-related cache. - Updated various services and controllers to utilize TOOL_CACHE instead of CONFIG_STORE for better separation of concerns in caching logic. - Enhanced .env.example with comments on using in-memory cache for blue/green deployments. * 🔧 refactor: Update cache configuration for in-memory storage handling - Enhanced the handling of `FORCED_IN_MEMORY_CACHE_NAMESPACES` in `cacheConfig.ts` to default to `CONFIG_STORE` and `APP_CONFIG`, ensuring safer blue/green deployments. - Updated `.env.example` with clearer comments regarding the usage of in-memory cache namespaces. - Improved unit tests to validate the new default behavior and handling of empty strings for cache namespaces.	2026-02-11 22:20:43 -05:00
Danny Avila	924be3b647	🛡️ fix: Implement TOCTOU-Safe SSRF Protection for Actions and MCP (#11722) ... * refactor: better SSRF Protection in Action and Tool Services - Added `createSSRFSafeAgents` function to create HTTP/HTTPS agents that block connections to private/reserved IP addresses, enhancing security against SSRF attacks. - Updated `createActionTool` to accept a `useSSRFProtection` parameter, allowing the use of SSRF-safe agents during tool execution. - Modified `processRequiredActions` and `loadAgentTools` to utilize the new SSRF protection feature based on allowed domains configuration. - Introduced `resolveHostnameSSRF` function to validate resolved IPs against private ranges, preventing potential SSRF vulnerabilities. - Enhanced tests for domain resolution and private IP detection to ensure robust SSRF protection mechanisms are in place. * feat: Implement SSRF protection in MCP connections - Added `createSSRFSafeUndiciConnect` function to provide SSRF-safe DNS lookup options for undici agents. - Updated `MCPConnection`, `MCPConnectionFactory`, and `ConnectionsRepository` to include `useSSRFProtection` parameter, enabling SSRF protection based on server configuration. - Enhanced `MCPManager` and `UserConnectionManager` to utilize SSRF protection when establishing connections. - Updated tests to validate the integration of SSRF protection across various components, ensuring robust security measures are in place. * refactor: WS MCPConnection with SSRF protection and async transport construction - Added `resolveHostnameSSRF` to validate WebSocket hostnames against private IP addresses, enhancing SSRF protection. - Updated `constructTransport` method to be asynchronous, ensuring proper handling of SSRF checks before establishing connections. - Improved error handling for WebSocket transport to prevent connections to potentially unsafe addresses. * test: Enhance ActionRequest tests for SSRF-safe agent passthrough - Added tests to verify that httpAgent and httpsAgent are correctly passed to axios.create when provided in ActionRequest. - Included scenarios to ensure agents are not included when no options are specified. - Enhanced coverage for POST requests to confirm agent passthrough functionality. - Improved overall test robustness for SSRF protection in ActionRequest execution.	2026-02-11 22:09:58 -05:00
Danny Avila	9054ca9c15	🆔 fix: Atomic File Dedupe, Bedrock Tokens Fix, and Allowed MIME Types (#11675) ... * feat: Add support for Apache Parquet MIME types - Introduced 'application/x-parquet' to the full MIME types list and code interpreter MIME types list. - Updated application MIME types regex to include 'x-parquet' and 'vnd.apache.parquet'. - Added mapping for '.parquet' files to 'application/x-parquet' in code type mapping, enhancing file format support. * feat: Implement atomic file claiming for code execution outputs - Added a new `claimCodeFile` function to atomically claim a file_id for code execution outputs, preventing duplicates by using a compound key of filename and conversationId. - Updated `processCodeOutput` to utilize the new claiming mechanism, ensuring that concurrent calls for the same filename converge on a single record. - Refactored related tests to validate the new atomic claiming behavior and its impact on file usage tracking and versioning. * fix: Update image file handling to use cache-busting filepath - Modified the `processCodeOutput` function to generate a cache-busting filepath for updated image files, improving browser caching behavior. - Adjusted related tests to reflect the change from versioned filenames to cache-busted filepaths, ensuring accurate validation of image updates. * fix: Update step handler to prevent undefined content for non-tool call types - Modified the condition in useStepHandler to ensure that undefined content is only assigned for specific content types, enhancing the robustness of content handling. * fix: Update bedrockOutputParser to handle maxTokens for adaptive models - Modified the bedrockOutputParser logic to ensure that maxTokens is not set for adaptive models when neither maxTokens nor maxOutputTokens are provided, improving the handling of adaptive thinking configurations. - Updated related tests to reflect these changes, ensuring accurate validation of the output for adaptive models. * chore: Update @librechat/agents to version 3.1.38 in package.json and package-lock.json * fix: Enhance file claiming and error handling in code processing - Updated the `processCodeOutput` function to use a consistent file ID for claiming files, preventing duplicates and improving concurrency handling. - Refactored the `createFileMethods` to include error handling for failed file claims, ensuring robust behavior when claiming files for conversations. - These changes enhance the reliability of file management in the application. * fix: Update adaptive thinking test for Opus 4.6 model - Modified the test for configuring adaptive thinking to reflect that no default maxTokens should be set for the Opus 4.6 model. - Updated assertions to ensure that maxTokens is undefined, aligning with the expected behavior for adaptive models.	2026-02-07 13:26:18 -05:00
Danny Avila	a771d70b10	🎬 fix: Code Session Context In Event Driven Mode (#11673) ... * 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.	2026-02-07 03:09:55 -05:00
Danny Avila	41e2348d47	🤖 feat: Claude Opus 4.6 - 1M Context, Premium Pricing, Adaptive Thinking (#11670) ... * 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.	2026-02-06 18:35:36 -05:00
Chiranjeevisantosh Madugundi	754d921b51	🧽 chore: Remove deprecated Claude models from Default List (#11639)	2026-02-05 15:07:45 +01:00
Danny Avila	8cf5ae7e79	🛡️ fix: Preserve CREATE/SHARE/SHARE_PUBLIC Permissions with Boolean Config (#11647) ... * 🔧 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.	2026-02-05 15:06:53 +01:00
Danny Avila	5eb0a3ad90	⚠️ chore: Remove Deprecated forcePrompt setting (#11622) ... - 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.	2026-02-04 11:02:27 +01:00
Danny Avila	f34052c6bb	🌙 feat: Moonshot Provider Support (#11621) ... * ✨ 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	2026-02-04 10:53:57 +01:00
Danny Avila	3ffc0c74bf	🎯 feat: Add Programmatic Tool Calling UI for MCP Tools (#11604) ... * 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.	2026-02-02 14:37:17 +01:00
Danny Avila	6279ea8dd7	🛸 feat: Remote Agent Access with External API Support (#11503) ... * 🪪 feat: Microsoft Graph Access Token Placeholder for MCP Servers (#10867) * feat: MCP Graph Token env var * Addressing copilot remarks * Addressed Copilot review remarks * Fixed graphtokenservice mock in MCP test suite * fix: remove unnecessary type check and cast in resolveGraphTokensInRecord * ci: add Graph Token integration tests in MCPManager * refactor: update user type definitions to use Partial<IUser> in multiple functions * test: enhance MCP tests for graph token processing and user placeholder resolution - Added comprehensive tests to validate the interaction between preProcessGraphTokens and processMCPEnv. - Ensured correct resolution of graph tokens and user placeholders in various configurations. - Mocked OIDC utilities to facilitate testing of token extraction and validation. - Verified that original options remain unchanged after processing. * chore: import order * chore: imports --------- Co-authored-by: Danny Avila <danny@librechat.ai> * WIP: OpenAI-compatible API for LibreChat agents - Added OpenAIChatCompletionController for handling chat completions. - Introduced ListModelsController and GetModelController for listing and retrieving agent details. - Created routes for OpenAI API endpoints, including /v1/chat/completions and /v1/models. - Developed event handlers for streaming responses in OpenAI format. - Implemented request validation and error handling for API interactions. - Integrated content aggregation and response formatting to align with OpenAI specifications. This commit establishes a foundational API for interacting with LibreChat agents in a manner compatible with OpenAI's chat completion interface. * refactor: OpenAI-spec content aggregation for improved performance and clarity * fix: OpenAI chat completion controller with safe user handling for correct tool loading * refactor: Remove conversation ID from OpenAI response context and related handlers * refactor: OpenAI chat completion handling with streaming support - Introduced a lightweight tracker for streaming responses, allowing for efficient tracking of emitted content and usage metadata. - Updated the OpenAIChatCompletionController to utilize the new tracker, improving the handling of streaming and non-streaming responses. - Refactored event handlers to accommodate the new streaming logic, ensuring proper management of tool calls and content aggregation. - Adjusted response handling to streamline error reporting during streaming sessions. * WIP: Open Responses API with core service, types, and handlers - Added Open Responses API module with comprehensive types and enums. - Implemented core service for processing requests, including validation and input conversion. - Developed event handlers for streaming responses and non-streaming aggregation. - Established response building logic and error handling mechanisms. - Created detailed types for input and output content, ensuring compliance with Open Responses specification. * feat: Implement response storage and retrieval in Open Responses API - Added functionality to save user input messages and assistant responses to the database when the `store` flag is set to true. - Introduced a new endpoint to retrieve stored responses by ID, allowing users to access previous interactions. - Enhanced the response creation process to include database operations for conversation and message storage. - Implemented tests to validate the storage and retrieval of responses, ensuring correct behavior for both existing and non-existent response IDs. * refactor: Open Responses API with additional token tracking and validation - Added support for tracking cached tokens in response usage, improving token management. - Updated response structure to include new properties for top log probabilities and detailed usage metrics. - Enhanced tests to validate the presence and types of new properties in API responses, ensuring compliance with updated specifications. - Refactored response handling to accommodate new fields and improve overall clarity and performance. * refactor: Update reasoning event handlers and types for consistency - Renamed reasoning text events to simplify naming conventions, changing `emitReasoningTextDelta` to `emitReasoningDelta` and `emitReasoningTextDone` to `emitReasoningDone`. - Updated event types in the API to reflect the new naming, ensuring consistency across the codebase. - Added `logprobs` property to output events for enhanced tracking of log probabilities. * feat: Add validation for streaming events in Open Responses API tests * feat: Implement response.created event in Open Responses API - Added emitResponseCreated function to emit the response.created event as the first event in the streaming sequence, adhering to the Open Responses specification. - Updated createResponse function to emit response.created followed by response.in_progress. - Enhanced tests to validate the order of emitted events, ensuring response.created is triggered before response.in_progress. * feat: Responses API with attachment event handling - Introduced `createResponsesToolEndCallback` to handle attachment events in the Responses API, emitting `librechat:attachment` events as per the Open Responses extension specification. - Updated the `createResponse` function to utilize the new callback for processing tool outputs and emitting attachments during streaming. - Added helper functions for writing attachment events and defined types for attachment data, ensuring compatibility with the Open Responses protocol. - Enhanced tests to validate the integration of attachment events within the Responses API workflow. * WIP: remote agent auth * fix: Improve loading state handling in AgentApiKeys component - Updated the rendering logic to conditionally display loading spinner and API keys based on the loading state. - Removed unnecessary imports and streamlined the component for better readability. * refactor: Update API key access handling in routes - Replaced `checkAccess` with `generateCheckAccess` for improved access control. - Consolidated access checks into a single `checkApiKeyAccess` function, enhancing code readability and maintainability. - Streamlined route definitions for creating, listing, retrieving, and deleting API keys. * fix: Add permission handling for REMOTE_AGENT resource type * feat: Enhance permission handling for REMOTE_AGENT resources - Updated the deleteAgent and deleteUserAgents functions to handle permissions for both AGENT and REMOTE_AGENT resource types. - Introduced new functions to enrich REMOTE_AGENT principals and backfill permissions for AGENT owners. - Modified createAgentHandler and duplicateAgentHandler to grant permissions for REMOTE_AGENT alongside AGENT. - Added utility functions for retrieving effective permissions for REMOTE_AGENT resources, ensuring consistent access control across the application. * refactor: Rename and update roles for remote agent access - Changed role name from API User to Editor in translation files for clarity. - Updated default editor role ID from REMOTE_AGENT_USER to REMOTE_AGENT_EDITOR in resource configurations. - Adjusted role localization to reflect the new Editor role. - Modified access permissions to align with the updated role definitions across the application. * feat: Introduce remote agent permissions and update access handling - Added support for REMOTE_AGENTS in permission schemas, including use, create, share, and share_public permissions. - Updated the interface configuration to include remote agent settings. - Modified middleware and API key access checks to align with the new remote agent permission structure. - Enhanced role defaults to incorporate remote agent permissions, ensuring consistent access control across the application. * refactor: Update AgentApiKeys component and permissions handling - Refactored the AgentApiKeys component to improve structure and readability, including the introduction of ApiKeysContent for better separation of concerns. - Updated CreateKeyDialog to accept an onKeyCreated callback, enhancing its functionality. - Adjusted permission checks in Data component to use REMOTE_AGENTS and USE permissions, aligning with recent permission schema changes. - Enhanced loading state handling and dialog management for a smoother user experience. * refactor: Update remote agent access checks in API routes - Replaced existing access checks with `generateCheckAccess` for remote agents in the API keys and agents routes. - Introduced specific permission checks for creating, listing, retrieving, and deleting API keys, enhancing access control. - Improved code structure by consolidating permission handling for remote agents across multiple routes. * fix: Correct query parameters in ApiKeysContent component - Updated the useGetAgentApiKeysQuery call to include an object for the enabled parameter, ensuring proper functionality when the component is open. - This change improves the handling of API key retrieval based on the component's open state. * feat: Implement remote agents permissions and update API routes - Added new API route for updating remote agents permissions, enhancing role management capabilities. - Introduced remote agents permissions handling in the AgentApiKeys component, including a dedicated settings dialog. - Updated localization files to include new remote agents permission labels for better user experience. - Refactored data provider to support remote agents permissions updates, ensuring consistent access control across the application. * feat: Add remote agents permissions to role schema and interface - Introduced new permissions for REMOTE_AGENTS in the role schema, including USE, CREATE, SHARE, and SHARE_PUBLIC. - Updated the IRole interface to reflect the new remote agents permissions structure, enhancing role management capabilities. * feat: Add remote agents settings button to API keys dialog * feat: Update AgentFooter to include remote agent sharing permissions - Refactored access checks to incorporate permissions for sharing remote agents. - Enhanced conditional rendering logic to allow sharing by users with remote agent permissions. - Improved loading state handling for remote agent permissions, ensuring a smoother user experience. * refactor: Update API key creation access check and localization strings - Replaced the access check for creating API keys to use the existing remote agents access check. - Updated localization strings to correct the descriptions for remote agent permissions, ensuring clarity in user interface. * fix: resource permission mapping to include remote agents - Changed the resourceToPermissionMap to use a Partial<Record> for better flexibility. - Added mapping for REMOTE_AGENT permissions, enhancing the sharing capabilities for remote agents. * feat: Implement remote access checks for agent models - Enhanced ListModelsController and GetModelController to include checks for user permissions on remote agents. - Integrated findAccessibleResources to filter agents based on VIEW permission for REMOTE_AGENT. - Updated response handling to ensure users can only access agents they have permissions for, improving security and access control. * fix: Update user parameter type in processUserPlaceholders function - Changed the user parameter type in the processUserPlaceholders function from Partial<Partial<IUser>> to Partial<IUser> for improved type clarity and consistency. * refactor: Simplify integration test structure by removing conditional describe - Replaced conditional describeWithApiKey with a standard describe for all integration tests in responses.spec.js. - This change enhances test clarity and ensures all tests are executed consistently, regardless of the SKIP_INTEGRATION_TESTS flag. * test: Update AgentFooter tests to reflect new grant access dialog ID - Changed test IDs for the grant access dialog in AgentFooter tests to include the resource type, ensuring accurate identification in the test cases. - This update improves test clarity and aligns with recent changes in the component's implementation. * test: Enhance integration tests for Open Responses API - Updated integration tests in responses.spec.js to utilize an authRequest helper for consistent authorization handling across all test cases. - Introduced a test user and API key creation to improve test setup and ensure proper permission checks for remote agents. - Added checks for existing access roles and created necessary roles if they do not exist, enhancing test reliability and coverage. * feat: Extend accessRole schema to include remoteAgent resource type - Updated the accessRole schema to add 'remoteAgent' to the resourceType enum, enhancing the flexibility of role assignments and permissions management. * test: refactored test setup to create a minimal Express app for responses routes, enhancing test structure and maintainability. * test: Enhance abort.spec.js by mocking additional modules for improved test isolation - Updated the test setup in abort.spec.js to include actual implementations of '@librechat/data-schemas' and '@librechat/api' while maintaining mock functionality. - This change improves test reliability and ensures that the tests are more representative of the actual module behavior. * refactor: Update conversation ID generation to use UUID - Replaced the nanoid with uuidv4 for generating conversation IDs in the createResponse function, enhancing uniqueness and consistency in ID generation. * test: Add remote agent access roles to AccessRole model tests - Included additional access roles for remote agents (REMOTE_AGENT_EDITOR, REMOTE_AGENT_OWNER, REMOTE_AGENT_VIEWER) in the AccessRole model tests to ensure comprehensive coverage of role assignments and permissions management. * chore: Add deletion of user agent API keys in user deletion process - Updated the user deletion process in UserController and delete-user.js to include the removal of user agent API keys, ensuring comprehensive cleanup of user data upon account deletion. * test: Add remote agents permissions to permissions.spec.ts - Enhanced the permissions tests by including comprehensive permission settings for remote agents across various scenarios, ensuring accurate validation of access controls for remote agent roles. * chore: Update remote agents translations for clarity and consistency - Removed outdated remote agents translation entries and added revised entries to improve clarity on API key creation and sharing permissions for remote agents. This enhances user understanding of the available functionalities. * feat: Add indexing and TTL for agent API keys - Introduced an index on the `key` field for improved query performance. - Added a TTL index on the `expiresAt` field to enable automatic cleanup of expired API keys, ensuring efficient management of stored keys. * chore: Update API route documentation for clarity - Revised comments in the agents route file to clarify the handling of API key authentication. - Removed outdated endpoint listings to streamline the documentation and focus on current functionality. --------- Co-authored-by: Max Sanna <max@maxsanna.com>	2026-01-28 17:44:33 -05:00
Dustin Healy	bb220f1af9	👤 feat: AWS Bedrock Custom Inference Profiles (#11308) ... * feat: add support for inferenceProfiles mapping * fix: remove friendly name since api requires actual model id for validation alongside inference profile * docs: more generic description in docs * chore: address comments * chore: update peer dependency versions in package.json - Bump @aws-sdk/client-bedrock-runtime from ^3.941.0 to ^3.970.0 - Update @librechat/agents from ^3.0.78 to ^3.0.79 * fix: update @librechat/agents dependency to version 3.0.80 * test: add unit tests for inference profile configuration in initializeBedrock function - Introduced tests to validate the applicationInferenceProfile setting based on model configuration. - Ensured correct handling of environment variables and fallback scenarios for inference profile ARNs. - Added cases for empty inferenceProfiles and absence of bedrock config to confirm expected behavior. * fix: update bedrock endpoint schema reference in config - Changed the bedrock endpoint reference from baseEndpointSchema to bedrockEndpointSchema for improved clarity and accuracy in configuration. * test: add unit tests for Bedrock endpoint configuration - Introduced tests to validate the configuration of Bedrock endpoints with models and inference profiles. - Added scenarios for both complete and minimal configurations to ensure expected behavior. - Enhanced coverage for the handling of inference profiles without a models array. --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-01-28 17:44:32 -05:00
Danny Avila	75c02a1a18	🗂️ feat: Better Persistence for Code Execution Files Between Sessions (#11362) ... * refactor: process code output files for re-use (WIP) * feat: file attachment handling with additional metadata for downloads * refactor: Update directory path logic for local file saving based on basePath * refactor: file attachment handling to support TFile type and improve data merging logic * feat: thread filtering of code-generated files - Introduced parentMessageId parameter in addedConvo and initialize functions to enhance thread management. - Updated related methods to utilize parentMessageId for retrieving messages and filtering code-generated files by conversation threads. - Enhanced type definitions to include parentMessageId in relevant interfaces for better clarity and usage. * chore: imports/params ordering * feat: update file model to use messageId for filtering and processing - Changed references from 'message' to 'messageId' in file-related methods for consistency. - Added messageId field to the file schema and updated related types. - Enhanced file processing logic to accommodate the new messageId structure. * feat: enhance file retrieval methods to support user-uploaded execute_code files - Added a new method `getUserCodeFiles` to retrieve user-uploaded execute_code files, excluding code-generated files. - Updated existing file retrieval methods to improve filtering logic and handle edge cases. - Enhanced thread data extraction to collect both message IDs and file IDs efficiently. - Integrated `getUserCodeFiles` into relevant endpoints for better file management in conversations. * chore: update @librechat/agents package version to 3.0.78 in package-lock.json and related package.json files * refactor: file processing and retrieval logic - Added a fallback mechanism for download URLs when files exceed size limits or cannot be processed locally. - Implemented a deduplication strategy for code-generated files based on conversationId and filename to optimize storage. - Updated file retrieval methods to ensure proper filtering by messageIds, preventing orphaned files from being included. - Introduced comprehensive tests for new thread data extraction functionality, covering edge cases and performance considerations. * fix: improve file retrieval tests and handling of optional properties - Updated tests to safely access optional properties using non-null assertions. - Modified test descriptions for clarity regarding the exclusion of execute_code files. - Ensured that the retrieval logic correctly reflects the expected outcomes for file queries. * test: add comprehensive unit tests for processCodeOutput functionality - Introduced a new test suite for the processCodeOutput function, covering various scenarios including file retrieval, creation, and processing for both image and non-image files. - Implemented mocks for dependencies such as axios, logger, and file models to isolate tests and ensure reliable outcomes. - Validated behavior for existing files, new file creation, and error handling, including size limits and fallback mechanisms. - Enhanced test coverage for metadata handling and usage increment logic, ensuring robust verification of file processing outcomes. * test: enhance file size limit enforcement in processCodeOutput tests - Introduced a configurable file size limit for tests to improve flexibility and coverage. - Mocked the `librechat-data-provider` to allow dynamic adjustment of file size limits during tests. - Updated the file size limit enforcement test to validate behavior when files exceed specified limits, ensuring proper fallback to download URLs. - Reset file size limit after tests to maintain isolation for subsequent test cases.	2026-01-28 17:44:32 -05:00