16 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	a01959b3d2	🛰️ fix: Cross-Replica Created Event Delivery (#12231) ... * fix: emit created event from metadata on cross-replica subscribe In multi-instance Redis deployments, the created event (which triggers sidebar conversation creation) was lost when the SSE subscriber connected to a different instance than the one generating. The event was only in the generating instance's local earlyEventBuffer and the Redis pub/sub message was already gone by the time the subscriber's channel was active. When subscribing cross-replica (empty buffer, Redis mode, userMessage already in job metadata), reconstruct and emit the created event directly from stored metadata. * test: add skipBufferReplay regression guard for cross-replica created event Add test asserting the resume path (skipBufferReplay: true) does NOT emit a created event on cross-replica subscribe — prevents the duplication fix from PR #12225 from regressing. Add explanatory JSDoc on the cross-replica fallback branch documenting which fields are preserved from trackUserMessage() and why sender/isCreatedByUser are hardcoded. * refactor: replace as-unknown-as casts with discriminated ServerSentEvent union Split ServerSentEvent into StreamEvent | CreatedEvent | FinalEvent so event shapes are statically typed. Removes all as-unknown-as casts in GenerationJobManager and test file; narrows with proper union members where properties are accessed. * fix: await trackUserMessage before PUBLISH for structural ordering trackUserMessage was fire-and-forget — the HSET for userMessage could theoretically race with the PUBLISH. Await it so the write commits before the pub/sub fires, guaranteeing any cross-replica getJob() after the pub/sub window always finds userMessage in Redis. No-op for non-created events (early return before any async work). * refactor: type CreatedEvent.message explicitly, fix JSDoc and import Give CreatedEvent.message its full known shape instead of Record<string, unknown>. Update sendEvent JSDoc to reflect the discriminated union. Use barrel import in test file. * refactor: type FinalEvent fields with explicit message and conversation shapes Replace Record<string, unknown> on requestMessage, responseMessage, conversation, and runMessages with FinalMessageFields and a typed conversation shape. Captures the known field set used by all final event constructors (abort handler in GenerationJobManager and normal completion in request.js) while allowing extension via index signature for fields contributed by the full TMessage/TConversation schemas. * refactor: narrow trackUserMessage with discriminated union, disambiguate error fields Use 'created' in event to narrow ServerSentEvent to CreatedEvent, eliminating all Record<string, unknown> casts and manual field assertions. Add JSDoc to the two distinct error fields on FinalMessageFields and FinalEvent to prevent confusion. * fix: update cross-replica test to expect created event from metadata The cross-replica subscribe fallback now correctly emits a created event reconstructed from persisted metadata when userMessage exists in the Redis job hash. Replica B receives 4 events (created + 3 deltas) instead of 3.	2026-03-15 11:11:10 -04:00
Danny Avila	7bc793b18d	🌊 fix: Prevent Buffered Event Duplication on SSE Resume Connections (#12225) ... * fix: skipBufferReplay for job resume connections - Introduced a new option `skipBufferReplay` in the `subscribe` method of `GenerationJobManagerClass` to prevent duplication of events when resuming a connection. - Updated the logic to conditionally skip replaying buffered events if a sync event has already been sent, enhancing the efficiency of event handling during reconnections. - Added integration tests to verify the correct behavior of the new option, ensuring that no buffered events are replayed when `skipBufferReplay` is true, while still allowing for normal replay behavior when false. * refactor: Update GenerationJobManager to handle sync events more efficiently - Modified the `subscribe` method to utilize a new `skipBufferReplay` option, allowing for the prevention of duplicate events during resume connections. - Enhanced the logic in the `chat/stream` route to conditionally skip replaying buffered events if a sync event has already been sent, improving event handling efficiency. - Updated integration tests to verify the correct behavior of the new option, ensuring that no buffered events are replayed when `skipBufferReplay` is true, while maintaining normal replay behavior when false. * test: Enhance GenerationJobManager integration tests for Redis mode - Updated integration tests to conditionally run based on the USE_REDIS environment variable, allowing for better control over Redis-related tests. - Refactored test descriptions to utilize a dynamic `describeRedis` function, improving clarity and organization of tests related to Redis functionality. - Removed redundant checks for Redis availability within individual tests, streamlining the test logic and enhancing readability. * fix: sync handler state for new messages on resume The sync event's else branch (new response message) was missing resetContentHandler() and syncStepMessage() calls, leaving stale handler state that caused subsequent deltas to build on partial content instead of the synced aggregatedContent. * feat: atomic subscribeWithResume to close resume event gap Replaces separate getResumeState() + subscribe() calls with a single subscribeWithResume() that atomically drains earlyEventBuffer between the resume snapshot and the subscribe. In in-memory mode, drained events are returned as pendingEvents for the client to replay after sync. In Redis mode, pendingEvents is empty since chunks are already persisted. The route handler now uses the atomic method for resume connections and extracted shared SSE write helpers to reduce duplication. The client replays any pendingEvents through the existing step/content handlers after applying aggregatedContent from the sync payload. * fix: only capture gap events in subscribeWithResume, not pre-snapshot buffer The previous implementation drained the entire earlyEventBuffer into pendingEvents, but pre-snapshot events are already reflected in aggregatedContent. Replaying them re-introduced the duplication bug through a different vector. Now records buffer length before getResumeState() and slices from that index, so only events arriving during the async gap are returned as pendingEvents. Also: - Handle pendingEvents when resumeState is null (replay directly) - Hoist duplicate test helpers to shared scope - Remove redundant writableEnded guard in onDone	2026-03-14 10:54:26 -04:00
Danny Avila	a0f9782e60	🪣 fix: Prevent Memory Retention from AsyncLocalStorage Context Propagation (#11942) ... * fix: store hide_sequential_outputs before processStream clears config processStream now clears config.configurable after completion to break memory retention chains. Save hide_sequential_outputs to a local variable before calling runAgents so the post-stream filter still works. * feat: memory diagnostics * chore: expose garbage collection in backend inspect command Updated the backend inspect command in package.json to include the --expose-gc flag, enabling garbage collection diagnostics for improved memory management during development. * chore: update @librechat/agents dependency to version 3.1.52 Bumped the version of @librechat/agents in package.json and package-lock.json to ensure compatibility and access to the latest features and fixes. * fix: clear heavy config state after processStream to prevent memory leaks Break the reference chain from LangGraph's internal __pregel_scratchpad through @langchain/core RunTree.extra[lc:child_config] into the AsyncLocalStorage context captured by timers and I/O handles. After stream completion, null out symbol-keyed scratchpad properties (currentTaskInput), config.configurable, and callbacks. Also call Graph.clearHeavyState() to release config, signal, content maps, handler registry, and tool sessions. * chore: fix imports for memory utils * chore: add circular dependency check in API build step Enhanced the backend review workflow to include a check for circular dependencies during the API build process. If a circular dependency is detected, an error message is displayed, and the process exits with a failure status. * chore: update API build step to include circular dependency detection Modified the backend review workflow to rename the API package installation step to reflect its new functionality, which now includes detection of circular dependencies during the build process. * chore: add memory diagnostics option to .env.example Included a commented-out configuration option for enabling memory diagnostics in the .env.example file, which logs heap and RSS snapshots every 60 seconds when activated. * chore: remove redundant agentContexts cleanup in disposeClient function Streamlined the disposeClient function by eliminating duplicate cleanup logic for agentContexts, ensuring efficient memory management during client disposal. * refactor: move runOutsideTracing utility to utils and update its usage Refactored the runOutsideTracing function by relocating it to the utils module for better organization. Updated the tool execution handler to utilize the new import, ensuring consistent tracing behavior during tool execution. * refactor: enhance connection management and diagnostics Added a method to ConnectionsRepository for retrieving the active connection count. Updated UserConnectionManager to utilize this new method for app connection count reporting. Refined the OAuthReconnectionTracker's getStats method to improve clarity in diagnostics. Introduced a new tracing utility in the utils module to streamline tracing context management. Additionally, added a safeguard in memory diagnostics to prevent unnecessary snapshot collection for very short intervals. * refactor: enhance tracing utility and add memory diagnostics tests Refactored the runOutsideTracing function to improve warning logic when the AsyncLocalStorage context is missing. Added tests for memory diagnostics and tracing utilities to ensure proper functionality and error handling. Introduced a new test suite for memory diagnostics, covering snapshot collection and garbage collection behavior.	2026-02-25 17:41:23 -05:00
Danny Avila	252a5cc7ca	🔗 fix: Preserve Stream State Across Reconnects to Prevent Reorder Buffer Desync (#11842) ... When all subscribers left a stream, both RedisEventTransport and InMemoryEventTransport deleted the entire stream state, destroying the allSubscribersLeftCallbacks and abortCallbacks registered by GenerationJobManager.createJob(). On the next subscribe/unsubscribe cycle, the callback that resets hasSubscriber was gone, causing syncReorderBuffer to be skipped on subsequent reconnects. This led to the reorder buffer expecting seq 0 while the publisher was at seq 300+, triggering a 500ms force-flush timeout and "skipping N missing messages" warnings. Fix: preserve stream state (callbacks, abort handlers) when the last subscriber leaves instead of deleting it. State is fully cleaned up by cleanup() when the job completes, aborts, or is collected by periodic orphan cleanup.	2026-02-18 01:57:34 -05:00
Danny Avila	3fa94e843c	⚛️ refactor: Redis Scalability Improvements for High-Throughput Deployments (#11840) ... * fix: Redis scalability improvements for high-throughput deployments Replace INCR+check+DECR race in concurrency middleware with atomic Lua scripts. The old approach allowed 3-4 concurrent requests through a limit of 2 at 300 req/s because another request could slip between the INCR returning and the DECR executing. The Lua scripts run atomically on the Redis server, eliminating the race window entirely. Add exponential backoff with jitter to all three Redis retry strategies (ioredis single-node, cluster, keyv). Previously all instances retried at the same millisecond after an outage, causing a connection storm. Batch the RedisJobStore cleanup loop into parallel chunks of 50. With 1000 stale jobs, this reduces cleanup from ~20s of sequential calls to ~2s. Also pipeline appendChunk (xadd + expire) into a single round-trip and refresh TTL on every chunk instead of only the first, preventing TTL expiry during long-running streams. Propagate publish errors in RedisEventTransport.emitDone and emitError so callers can detect dropped completion/error events. emitChunk is left as swallow-and-log because its callers fire-and-forget without await. Add jest.config.js for the API package with babel TypeScript support and path alias resolution. Fix existing stream integration tests that were silently broken due to missing USE_REDIS_CLUSTER=false env var. * chore: Migrate Jest configuration from jest.config.js to jest.config.mjs Removed the old jest.config.js file and integrated the Jest configuration into jest.config.mjs, adding Babel TypeScript support and path alias resolution. This change streamlines the configuration for the API package. * fix: Ensure Redis retry delays do not exceed maximum configured delay Updated the delay calculation in Redis retry strategies to enforce a maximum delay defined in the configuration. This change prevents excessive delays during reconnection attempts, improving overall connection stability and performance. * fix: Update RedisJobStore cleanup to handle job failures gracefully Changed the cleanup process in RedisJobStore to use Promise.allSettled instead of Promise.all, allowing for individual job failures to be logged without interrupting the entire cleanup operation. This enhances error handling and provides better visibility into issues during job cleanup.	2026-02-18 00:04:33 -05:00
Danny Avila	e142ab72da	🔒 fix: Prevent Race Condition in RedisJobStore (#11764) ... * 🔧 fix: Optimize job update logic in RedisJobStore - Refactored the updateJob method to use a Lua script for atomic updates, ensuring that jobs are only updated if they exist in Redis. - Removed redundant existence check and streamlined the serialization process for better performance and clarity. * 🔧 test: Add race condition tests for RedisJobStore - Introduced tests to verify behavior of updateJob after deleteJob, ensuring no job hash is recreated post-deletion. - Added checks for orphan keys when concurrent deleteJob and updateJob operations occur, enhancing reliability in job management. * 🔧 test: Refactor Redis client readiness checks in violationCache tests - Introduced a new helper function `waitForRedisClients` to streamline the readiness checks for Redis clients in the violationCache integration tests. - Removed redundant Redis client readiness checks from individual test cases, improving code clarity and maintainability. * 🔧 fix: Update RedisJobStore to use hset instead of hmset - Replaced instances of `hmset` with `hset` in the RedisJobStore implementation to align with the latest Redis command updates. - Updated Lua script in the eval method to reflect the change, ensuring consistent job handling in both cluster and non-cluster modes.	2026-02-12 18:47:57 -05:00
Danny Avila	e646a3615e	🌊 fix: Prevent Truncations When Redis Resumable Streams Are Enabled (#11710) ... * fix: prevent truncated responses when Redis resumable streams are enabled Race condition in RedisEventTransport.subscribe() caused early events (seq 0+) to be lost. The Redis SUBSCRIBE command was fired as fire-and-forget, but GenerationJobManager immediately set hasSubscriber=true, disabling the earlyEventBuffer. Events published during the gap between subscribe() returning and the Redis subscription actually taking effect were neither buffered nor received — they were silently dropped by Pub/Sub. This manifested as "timeout waiting for seq 0, force-flushing N messages" warnings followed by truncated or missing response text in the UI. The fix: - IEventTransport.subscribe() now returns an optional `ready` promise that resolves once the transport can actually receive messages - RedisEventTransport returns the Redis SUBSCRIBE acknowledgment as the `ready` promise instead of firing it as fire-and-forget - GenerationJobManager.subscribe() awaits `ready` before setting hasSubscriber=true, keeping the earlyEventBuffer active during the subscription window so no events are lost - GenerationJobManager.emitChunk() early-returns after buffering when no subscriber is connected, avoiding wasteful Redis PUBLISHes that nobody would receive Adds 5 regression tests covering the race condition for both in-memory and Redis transports, verifying that events emitted before subscribe are buffered and replayed, that the ready promise contract is correct for both transport implementations, and that no events are lost across the subscribe boundary. * refactor: Update import paths in GenerationJobManager integration tests - Refactored import statements in the GenerationJobManager integration test file to use absolute paths instead of relative paths, improving code readability and maintainability. - Removed redundant imports and ensured consistent usage of the updated import structure across the test cases. * chore: Remove redundant await from GenerationJobManager initialization in tests - Updated multiple test cases to call GenerationJobManager.initialize() without awaiting, improving test performance and clarity. - Ensured consistent initialization across various scenarios in the CollectedUsage and AbortJob test suites. * refactor: Enhance GenerationJobManager integration tests and RedisEventTransport cleanup - Updated GenerationJobManager integration tests to utilize dynamic Redis clients and removed unnecessary awaits from initialization calls, improving test performance. - Refactored RedisEventTransport's destroy method to safely disconnect the subscriber, enhancing resource management and preventing potential errors during cleanup. * feat: Enhance GenerationJobManager and RedisEventTransport for improved event handling - Added a resetSequence method to IEventTransport and implemented it in RedisEventTransport to manage publish sequence counters effectively. - Updated GenerationJobManager to utilize the new resetSequence method, ensuring proper event handling during stream operations. - Introduced integration tests for GenerationJobManager to validate cross-replica event publishing and subscriber readiness in Redis, enhancing test coverage and reliability. * test: Add integration tests for GenerationJobManager sequence reset and error recovery with Redis - Introduced new tests to validate the behavior of GenerationJobManager during sequence resets, ensuring no stale events are received after a reset. - Added tests to confirm that the sequence is not reset when a second subscriber joins mid-stream, maintaining event integrity. - Implemented a test for resubscription after a Redis subscribe failure, verifying that events can still be received post-error. - Enhanced overall test coverage for Redis-related functionalities in GenerationJobManager. * fix: Update GenerationJobManager and RedisEventTransport for improved event synchronization - Replaced the resetSequence method with syncReorderBuffer in GenerationJobManager to enhance cross-replica event handling without resetting the publisher sequence. - Added a new syncReorderBuffer method in RedisEventTransport to advance the subscriber reorder buffer safely, ensuring no data loss during subscriber transitions. - Introduced a new integration test to validate that local subscribers joining do not cause data loss for cross-replica subscribers, enhancing the reliability of event delivery. - Updated existing tests to reflect changes in event handling logic, improving overall test coverage and robustness. * fix: Clear flushTimeout in RedisEventTransport to prevent potential memory leaks - Added logic to clear the flushTimeout in the reorderBuffer when resetting the sequence counters, ensuring proper resource management and preventing memory leaks during state transitions in RedisEventTransport.	2026-02-10 13:16:29 -05:00
Danny Avila	feb72ad2dc	🔄 refactor: Sequential Event Ordering in Redis Streaming Mode (#11650) ... * chore: linting image context file * refactor: Event Emission with Async Handling for Redis Ordering - Updated emitEvent and related functions to be async, ensuring proper event ordering in Redis mode. - Refactored multiple handlers to await emitEvent calls, improving reliability for streaming deltas. - Enhanced GenerationJobManager to await chunk emissions, critical for maintaining sequential event delivery. - Added tests to verify that events are delivered in strict order when using Redis, addressing previous issues with out-of-order messages. * refactor: Clear Pending Buffers and Timeouts in RedisEventTransport - Enhanced the cleanup process in RedisEventTransport by ensuring that pending messages and flush timeouts are cleared when the last subscriber unsubscribes. - Updated the destroy method to also clear pending messages and flush timeouts for all streams, improving resource management and preventing memory leaks. * refactor: Update Event Emission to Async for Improved Ordering - Refactored GenerationJobManager and RedisEventTransport to make emitDone and emitError methods async, ensuring proper event ordering in Redis mode. - Updated all relevant calls to await these methods, enhancing reliability in event delivery. - Adjusted tests to verify that events are processed in the correct sequence, addressing previous issues with out-of-order messages. * refactor: Adjust RedisEventTransport for 0-Indexed Sequence Handling - Updated sequence handling in RedisEventTransport to be 0-indexed, ensuring consistency across event emissions and buffer management. - Modified integration tests to reflect the new sequence logic, improving the accuracy of event processing and delivery order. - Enhanced comments for clarity on sequence management and terminal event handling. * chore: Add Redis dump file to .gitignore - Included dump.rdb in .gitignore to prevent accidental commits of Redis database dumps, enhancing repository cleanliness and security. * test: Increase wait times in RedisEventTransport integration tests for CI stability - Adjusted wait times for subscription establishment and event propagation from 100ms and 200ms to 500ms to improve reliability in CI environments. - Enhanced code readability by formatting promise resolution lines for better clarity.	2026-02-05 17:57:33 +01:00
Danny Avila	d13037881a	🔐 fix: MCP OAuth Tool Discovery and Event Emission (#11599) ... * fix: MCP OAuth tool discovery and event emission in event-driven mode - Add discoverServerTools method to MCPManager for tool discovery when OAuth is required - Fix OAuth event emission to send both ON_RUN_STEP and ON_RUN_STEP_DELTA events - Fix hasSubscriber flag reset in GenerationJobManager for proper event buffering - Add ToolDiscoveryOptions and ToolDiscoveryResult types - Update reinitMCPServer to use new discovery method and propagate OAuth URLs * refactor: Update ToolService and MCP modules for improved functionality - Reintroduced Constants in ToolService for better reference management. - Enhanced loadToolDefinitionsWrapper to handle both response and streamId scenarios. - Updated MCP module to correct type definitions for oauthStart parameter. - Improved MCPConnectionFactory to ensure proper disconnection handling during tool discovery. - Adjusted tests to reflect changes in mock implementations and ensure accurate behavior during OAuth handling. * fix: Refine OAuth handling in MCPConnectionFactory and related tests - Updated the OAuth URL assignment logic in reinitMCPServer to prevent overwriting existing URLs. - Enhanced error logging to provide clearer messages when tool discovery fails. - Adjusted tests to reflect changes in OAuth handling, ensuring accurate detection of OAuth requirements without generating URLs in discovery mode. * refactor: Clean up OAuth URL assignment in reinitMCPServer - Removed redundant OAuth URL assignment logic in the reinitMCPServer function to streamline the tool discovery process. - Enhanced error logging for tool discovery failures, improving clarity in debugging and monitoring. * fix: Update response handling in ToolService for event-driven mode - Changed the condition in loadToolDefinitionsWrapper to check for writableEnded instead of headersSent, ensuring proper event emission when the response is still writable. - This adjustment enhances the reliability of event handling during tool execution, particularly in streaming scenarios.	2026-02-01 19:37:04 -05:00
Danny Avila	36c5a88c4e	💰 fix: Multi-Agent Token Spending & Prevent Double-Spend (#11433) ... * fix: Token Spending Logic for Multi-Agents on Abort Scenarios * Implemented logic to skip token spending if a conversation is aborted, preventing double-spending. * Introduced `spendCollectedUsage` function to handle token spending for multiple models during aborts, ensuring accurate accounting for parallel agents. * Updated `GenerationJobManager` to store and retrieve collected usage data for improved abort handling. * Added comprehensive tests for the new functionality, covering various scenarios including cache token handling and parallel agent usage. * fix: Memory Context Handling for Multi-Agents * Refactored `buildMessages` method to pass memory context to parallel agents, ensuring they share the same user context. * Improved handling of memory context when no existing instructions are present for parallel agents. * Added comprehensive tests to verify memory context propagation and behavior under various scenarios, including cases with no memory available and empty agent configurations. * Enhanced logging for better traceability of memory context additions to agents. * chore: Memory Context Documentation for Parallel Agents * Updated documentation in the `AgentClient` class to clarify the in-place mutation of agentConfig objects when passing memory context to parallel agents. * Added notes on the implications of mutating objects directly to ensure all parallel agents receive the correct memory context before execution. * chore: UsageMetadata Interface docs for Token Spending * Expanded the UsageMetadata interface to support both OpenAI and Anthropic cache token formats. * Added detailed documentation for cache token properties, including mutually exclusive fields for different model types. * Improved clarity on how to access cache token details for accurate token spending tracking. * fix: Enhance Token Spending Logic in Abort Middleware * Refactored `spendCollectedUsage` function to utilize Promise.all for concurrent token spending, improving performance and ensuring all operations complete before clearing the collectedUsage array. * Added documentation to clarify the importance of clearing the collectedUsage array to prevent double-spending in abort scenarios. * Updated tests to verify the correct behavior of the spending logic and the clearing of the array after spending operations.	2026-01-20 14:43:19 -05:00
Danny Avila	c378e777ef	🪵 refactor: Preserve Job Error State for Late Stream Subscribers (#11372) ... * 🪵 refactor: Preserve job error state for late stream subscribers * 🔧 fix: Enhance error handling for late subscribers in GenerationJobManager - Implemented a cleanup strategy for error jobs to prevent immediate deletion, allowing late clients to receive error messages. - Updated job status handling to prioritize error notifications over completion events. - Added integration tests to verify error preservation and proper notification to late subscribers, including scenarios with Redis support.	2026-01-15 23:02:03 -05:00
Danny Avila	f8774983a0	🪪 fix: Misleading MCP Server Lookup Method Name (#11315) ... * 🔧 fix: MCP server ID resolver in access permissions (#11315) - Replaced `findMCPServerById` with `findMCPServerByObjectId` in access permissions route and corresponding tests for improved clarity and consistency in resource identification. * 🔧 refactor: Update MCP server resource access methods to use server name - Replaced instances of `findMCPServerById` with `findMCPServerByServerName` across middleware, database, and test files for improved clarity and consistency in resource identification. - Updated related comments and test cases to reflect the change in method usage. * chore: Increase timeout for Redis update in GenerationJobManager integration tests - Updated the timeout duration from 50ms to 200ms in the GenerationJobManager integration tests to ensure reliable verification of final event data in Redis after emitting the done event.	2026-01-12 21:04:25 -05:00
Danny Avila	a7645f4705	🪐 feat: Cross-replica support in GenerationJobManager for Redis mode (#11233) ... * feat: Implement cross-replica support in GenerationJobManager for Redis mode - Enhanced GenerationJobManager to support cross-replica scenarios by lazily creating runtime states from Redis when jobs exist but are not present in local memory. - Added functionality to persist `syncSent` and `finalEvent` states to Redis for consistency across replicas. - Implemented abort signal handling to allow replicas to receive and respond to abort requests from other instances, ensuring proper job termination. - Updated tests to validate cross-replica behavior, including job retrieval, subscription, and abort signal propagation. This update improves the robustness and reliability of job management in distributed environments. * fix: Enhance error handling and implement abort signal for cross-replica jobs in GenerationJobManager - Added error handling for Redis job updates in GenerationJobManager to log failures when persisting `syncSent` and `finalEvent` states. - Implemented a listener for cross-replica abort signals, ensuring that lazily-initialized jobs can respond to abort requests from other replicas. - Introduced a new integration test to validate the handling of abort signals for lazily-initialized jobs across replicas. These changes improve the reliability and robustness of job management in distributed environments.	2026-01-06 11:39:24 -05:00
Danny Avila	439bc98682	⏸ refactor: Improve UX for Parallel Streams (Multi-Convo) (#11096) ... * 🌊 feat: Implement multi-conversation feature with added conversation context and payload adjustments * refactor: Replace isSubmittingFamily with isSubmitting across message components for consistency * feat: Add loadAddedAgent and processAddedConvo for multi-conversation agent execution * refactor: Update ContentRender usage to conditionally render PlaceholderRow based on isLast and isSubmitting * WIP: first pass, sibling index * feat: Enhance multi-conversation support with agent tracking and display improvements * refactor: Introduce isEphemeralAgentId utility and update related logic for agent handling * refactor: Implement createDualMessageContent utility for sibling message display and enhance useStepHandler for added conversations * refactor: duplicate tools for added agent if ephemeral and primary agent is also ephemeral * chore: remove deprecated multimessage rendering * refactor: enhance dual message content creation and agent handling for parallel rendering * refactor: streamline message rendering and submission handling by removing unused state and optimizing conditional logic * refactor: adjust content handling in parallel mode to utilize existing content for improved agent display * refactor: update @librechat/agents dependency to version 3.0.53 * refactor: update @langchain/core and @librechat/agents dependencies to latest versions * refactor: remove deprecated @langchain/core dependency from package.json * chore: remove unused SearchToolConfig and GetSourcesParams types from web.ts * refactor: remove unused message properties from Message component * refactor: enhance parallel content handling with groupId support in ContentParts and useStepHandler * refactor: implement parallel content styling in Message, MessageRender, and ContentRender components. use explicit model name * refactor: improve agent ID handling in createDualMessageContent for dual message display * refactor: simplify title generation in AddedConvo by removing unused sender and preset logic * refactor: replace string interpolation with cn utility for className in HoverButtons component * refactor: enhance agent ID handling by adding suffix management for parallel agents and updating related components * refactor: enhance column ordering in ContentParts by sorting agents with suffix management * refactor: update @librechat/agents dependency to version 3.0.55 * feat: implement parallel content rendering with metadata support - Added `ParallelContentRenderer` and `ParallelColumns` components for rendering messages in parallel based on groupId and agentId. - Introduced `contentMetadataMap` to store metadata for each content part, allowing efficient parallel content detection. - Updated `Message` and `ContentRender` components to utilize the new metadata structure for rendering. - Modified `useStepHandler` to manage content indices and metadata during message processing. - Enhanced `IJobStore` interface and its implementations to support storing and retrieving content metadata. - Updated data schemas to include `contentMetadataMap` for messages, enabling multi-agent and parallel execution scenarios. * refactor: update @librechat/agents dependency to version 3.0.56 * refactor: remove unused EPHEMERAL_AGENT_ID constant and simplify agent ID check * refactor: enhance multi-agent message processing and primary agent determination * refactor: implement branch message functionality for parallel responses * refactor: integrate added conversation retrieval into message editing and regeneration processes * refactor: remove unused isCard and isMultiMessage props from MessageRender and ContentRender components * refactor: update @librechat/agents dependency to version 3.0.60 * refactor: replace usage of EPHEMERAL_AGENT_ID constant with isEphemeralAgentId function for improved clarity and consistency * refactor: standardize agent ID format in tests for consistency * chore: move addedConvo property to the correct position in payload construction * refactor: rename agent_id values in loadAgent tests for clarity * chore: reorder props in ContentParts component for improved readability * refactor: rename variable 'content' to 'result' for clarity in RedisJobStore tests * refactor: streamline useMessageActions by removing duplicate handleFeedback assignment * chore: revert placeholder rendering logic MessageRender and ContentRender components to original * refactor: implement useContentMetadata hook for optimized content metadata handling * refactor: remove contentMetadataMap and related logic from the codebase and revert back to agentId/groupId in content parts - Eliminated contentMetadataMap from various components and services, simplifying the handling of message content. - Updated functions to directly access agentId and groupId from content parts instead of relying on a separate metadata map. - Adjusted related hooks and components to reflect the removal of contentMetadataMap, ensuring consistent handling of message content. - Updated tests and documentation to align with the new structure of message content handling. * refactor: remove logging from groupParallelContent function to clean up output * refactor: remove model parameter from TBranchMessageRequest type for simplification * refactor: enhance branch message creation by stripping metadata for standalone content * chore: streamline branch message creation by simplifying content filtering and removing unnecessary metadata checks * refactor: include attachments in branch message creation for improved content handling * refactor: streamline agent content processing by consolidating primary agent identification and filtering logic * refactor: simplify multi-agent message processing by creating a dedicated mapping method and enhancing content filtering * refactor: remove unused parameter from loadEphemeralAgent function for cleaner code * refactor: update groupId handling in metadata to only set when provided by the server	2025-12-25 01:43:54 -05:00
Danny Avila	0ae3b87b65	🌊 feat: Resumable LLM Streams with Horizontal Scaling (#10926) ... * ✨ feat: Implement Resumable Generation Jobs with SSE Support - Introduced GenerationJobManager to handle resumable LLM generation jobs independently of HTTP connections. - Added support for subscribing to ongoing generation jobs via SSE, allowing clients to reconnect and receive updates without losing progress. - Enhanced existing agent controllers and routes to integrate resumable functionality, including job creation, completion, and error handling. - Updated client-side hooks to manage adaptive SSE streams, switching between standard and resumable modes based on user settings. - Added UI components and settings for enabling/disabling resumable streams, improving user experience during unstable connections. * WIP: resuming * WIP: resumable stream * feat: Enhance Stream Management with Abort Functionality - Updated the abort endpoint to support aborting ongoing generation streams using either streamId or conversationId. - Introduced a new mutation hook `useAbortStreamMutation` for client-side integration. - Added `useStreamStatus` query to monitor stream status and facilitate resuming conversations. - Enhanced `useChatHelpers` to incorporate abort functionality when stopping generation. - Improved `useResumableSSE` to handle stream errors and token refresh seamlessly. - Updated `useResumeOnLoad` to check for active streams and resume conversations appropriately. * fix: Update query parameter handling in useChatHelpers - Refactored the logic for determining the query parameter used in fetching messages to prioritize paramId from the URL, falling back to conversationId only if paramId is not available. This change ensures consistency with the ChatView component's expectations. * fix: improve syncing when switching conversations * fix: Prevent memory leaks in useResumableSSE by clearing handler maps on stream completion and cleanup * fix: Improve content type mismatch handling in useStepHandler - Enhanced the condition for detecting content type mismatches to include additional checks, ensuring more robust validation of content types before processing updates. * fix: Allow dynamic content creation in useChatFunctions - Updated the initial response handling to avoid pre-initializing content types, enabling dynamic creation of content parts based on incoming delta events. This change supports various content types such as think and text. * fix: Refine response message handling in useStepHandler - Updated logic to determine the appropriate response message based on the last message's origin, ensuring correct message replacement or appending based on user interaction. This change enhances the accuracy of message updates in the chat flow. * refactor: Enhance GenerationJobManager with In-Memory Implementations - Introduced InMemoryJobStore, InMemoryEventTransport, and InMemoryContentState for improved job management and event handling. - Updated GenerationJobManager to utilize these new implementations, allowing for better separation of concerns and easier maintenance. - Enhanced job metadata handling to support user messages and response IDs for resumable functionality. - Improved cleanup and state management processes to prevent memory leaks and ensure efficient resource usage. * refactor: Enhance GenerationJobManager with improved subscriber handling - Updated RuntimeJobState to include allSubscribersLeftHandlers for managing client disconnections without affecting subscriber count. - Refined createJob and subscribe methods to ensure generation starts only when the first real client connects. - Added detailed documentation for methods and properties to clarify the synchronization of job generation with client readiness. - Improved logging for subscriber checks and event handling to facilitate debugging and monitoring. * chore: Adjust timeout for subscriber readiness in ResumableAgentController - Reduced the timeout duration from 5000ms to 2500ms in the startGeneration function to improve responsiveness when waiting for subscriber readiness. This change aims to enhance the efficiency of the agent's background generation process. * refactor: Update GenerationJobManager documentation and structure - Enhanced the documentation for GenerationJobManager to clarify the architecture and pluggable service design. - Updated comments to reflect the potential for Redis integration and the need for async refactoring. - Improved the structure of the GenerationJob facade to emphasize the unified API while allowing for implementation swapping without affecting consumer code. * refactor: Convert GenerationJobManager methods to async for improved performance - Updated methods in GenerationJobManager and InMemoryJobStore to be asynchronous, enhancing the handling of job creation, retrieval, and management. - Adjusted the ResumableAgentController and related routes to await job operations, ensuring proper flow and error handling. - Increased timeout duration in ResumableAgentController's startGeneration function to 3500ms for better subscriber readiness management. * refactor: Simplify initial response handling in useChatFunctions - Removed unnecessary pre-initialization of content types in the initial response, allowing for dynamic content creation based on incoming delta events. This change enhances flexibility in handling various content types in the chat flow. * refactor: Clarify content handling logic in useStepHandler - Updated comments to better explain the handling of initialContent and existingContent in edit and resume scenarios. - Simplified the logic for merging content, ensuring that initialContent is used directly when available, improving clarity and maintainability. * refactor: Improve message handling logic in useStepHandler - Enhanced the logic for managing messages in multi-tab scenarios, ensuring that the most up-to-date message history is utilized. - Removed existing response placeholders and ensured user messages are included, improving the accuracy of message updates in the chat flow. * fix: remove unnecessary content length logging in the chat stream response, simplifying the debug message while retaining essential information about run steps. This change enhances clarity in logging without losing critical context. * refactor: Integrate streamId handling for improved resumable functionality for attachments - Added streamId parameter to various functions to support resumable mode in tool loading and memory processing. - Updated related methods to ensure proper handling of attachments and responses based on the presence of streamId, enhancing the overall streaming experience. - Improved logging and attachment management to accommodate both standard and resumable modes. * refactor: Streamline abort handling and integrate GenerationJobManager for improved job management - Removed the abortControllers middleware and integrated abort handling directly into GenerationJobManager. - Updated abortMessage function to utilize GenerationJobManager for aborting jobs by conversation ID, enhancing clarity and efficiency. - Simplified cleanup processes and improved error handling during abort operations. - Enhanced metadata management for jobs, including endpoint and model information, to facilitate better tracking and resource management. * refactor: Unify streamId and conversationId handling for improved job management - Updated ResumableAgentController and AgentController to generate conversationId upfront, ensuring it matches streamId for consistency. - Simplified job creation and metadata management by removing redundant conversationId updates from callbacks. - Refactored abortMiddleware and related methods to utilize the unified streamId/conversationId approach, enhancing clarity in job handling. - Removed deprecated methods from GenerationJobManager and InMemoryJobStore, streamlining the codebase and improving maintainability. * refactor: Enhance resumable SSE handling with improved UI state management and error recovery - Added UI state restoration on successful SSE connection to indicate ongoing submission. - Implemented detailed error handling for network failures, including retry logic with exponential backoff. - Introduced abort event handling to reset UI state on intentional stream closure. - Enhanced debugging capabilities for testing reconnection and clean close scenarios. - Updated generation function to retry on network errors, improving resilience during submission processes. * refactor: Consolidate content state management into IJobStore for improved job handling - Removed InMemoryContentState and integrated its functionality into InMemoryJobStore, streamlining content state management. - Updated GenerationJobManager to utilize jobStore for content state operations, enhancing clarity and reducing redundancy. - Introduced RedisJobStore for horizontal scaling, allowing for efficient job management and content reconstruction from chunks. - Updated IJobStore interface to reflect changes in content state handling, ensuring consistency across implementations. * feat: Introduce Redis-backed stream services for enhanced job management - Added createStreamServices function to configure job store and event transport, supporting both Redis and in-memory options. - Updated GenerationJobManager to allow configuration with custom job stores and event transports, improving flexibility for different deployment scenarios. - Refactored IJobStore interface to support asynchronous content retrieval, ensuring compatibility with Redis implementations. - Implemented RedisEventTransport for real-time event delivery across instances, enhancing scalability and responsiveness. - Updated InMemoryJobStore to align with new async patterns for content and run step retrieval, ensuring consistent behavior across storage options. * refactor: Remove redundant debug logging in GenerationJobManager and RedisEventTransport - Eliminated unnecessary debug statements in GenerationJobManager related to subscriber actions and job updates, enhancing log clarity. - Removed debug logging in RedisEventTransport for subscription and subscriber disconnection events, streamlining the logging output. - Cleaned up debug messages in RedisJobStore to focus on essential information, improving overall logging efficiency. * refactor: Enhance job state management and TTL configuration in RedisJobStore - Updated the RedisJobStore to allow customizable TTL values for job states, improving flexibility in job management. - Refactored the handling of job expiration and cleanup processes to align with new TTL configurations. - Simplified the response structure in the chat status endpoint by consolidating state retrieval, enhancing clarity and performance. - Improved comments and documentation for better understanding of the changes made. * refactor: cleanupOnComplete option to GenerationJobManager for flexible resource management - Introduced a new configuration option, cleanupOnComplete, allowing immediate cleanup of event transport and job resources upon job completion. - Updated completeJob and abortJob methods to respect the cleanupOnComplete setting, enhancing memory management. - Improved cleanup logic in the cleanup method to handle orphaned resources effectively. - Enhanced documentation and comments for better clarity on the new functionality. * refactor: Update TTL configuration for completed jobs in InMemoryJobStore - Changed the TTL for completed jobs from 5 minutes to 0, allowing for immediate cleanup. - Enhanced cleanup logic to respect the new TTL setting, improving resource management. - Updated comments for clarity on the behavior of the TTL configuration. * refactor: Enhance RedisJobStore with local graph caching for improved performance - Introduced a local cache for graph references using WeakRef to optimize reconnects for the same instance. - Updated job deletion and cleanup methods to manage the local cache effectively, ensuring stale entries are removed. - Enhanced content retrieval methods to prioritize local cache access, reducing Redis round-trips for same-instance reconnects. - Improved documentation and comments for clarity on the caching mechanism and its benefits. * feat: Add integration tests for GenerationJobManager, RedisEventTransport, and RedisJobStore, add Redis Cluster support - Introduced comprehensive integration tests for GenerationJobManager, covering both in-memory and Redis modes to ensure consistent job management and event handling. - Added tests for RedisEventTransport to validate pub/sub functionality, including cross-instance event delivery and error handling. - Implemented integration tests for RedisJobStore, focusing on multi-instance job access, content reconstruction from chunks, and consumer group behavior. - Enhanced test setup and teardown processes to ensure a clean environment for each test run, improving reliability and maintainability. * fix: Improve error handling in GenerationJobManager for allSubscribersLeft handlers - Enhanced the error handling logic when retrieving content parts for allSubscribersLeft handlers, ensuring that any failures are logged appropriately. - Updated the promise chain to catch errors from getContentParts, improving robustness and clarity in error reporting. * ci: Improve Redis client disconnection handling in integration tests - Updated the afterAll cleanup logic in integration tests for GenerationJobManager, RedisEventTransport, and RedisJobStore to use `quit()` for graceful disconnection of the Redis client. - Added fallback to `disconnect()` if `quit()` fails, enhancing robustness in resource management during test teardown. - Improved comments for clarity on the disconnection process and error handling. * refactor: Enhance GenerationJobManager and event transports for improved resource management - Updated GenerationJobManager to prevent immediate cleanup of eventTransport upon job completion, allowing final events to transmit fully before cleanup. - Added orphaned stream cleanup logic in GenerationJobManager to handle streams without corresponding jobs. - Introduced getTrackedStreamIds method in both InMemoryEventTransport and RedisEventTransport for better management of orphaned streams. - Improved comments for clarity on resource management and cleanup processes. * refactor: Update GenerationJobManager and ResumableAgentController for improved event handling - Modified GenerationJobManager to resolve readyPromise immediately, eliminating startup latency and allowing early event buffering for late subscribers. - Enhanced event handling logic to replay buffered events when the first subscriber connects, ensuring no events are lost due to race conditions. - Updated comments for clarity on the new event synchronization mechanism and its benefits in both Redis and in-memory modes. * fix: Update cache integration test command for stream to ensure proper execution - Modified the test command for cache integration related to streams by adding the --forceExit flag to prevent hanging tests. - This change enhances the reliability of the test suite by ensuring all tests complete as expected. * feat: Add active job management for user and show progress in conversation list - Implemented a new endpoint to retrieve active generation job IDs for the current user, enhancing user experience by allowing visibility of ongoing tasks. - Integrated active job tracking in the Conversations component, displaying generation indicators based on active jobs. - Optimized job management in the GenerationJobManager and InMemoryJobStore to support user-specific job queries, ensuring efficient resource handling and cleanup. - Updated relevant components and hooks to utilize the new active jobs feature, improving overall application responsiveness and user feedback. * feat: Implement active job tracking by user in RedisJobStore - Added functionality to retrieve active job IDs for a specific user, enhancing user experience by allowing visibility of ongoing tasks. - Implemented self-healing cleanup for stale job entries, ensuring accurate tracking of active jobs. - Updated job creation, update, and deletion methods to manage user-specific job sets effectively. - Enhanced integration tests to validate the new user-specific job management features. * refactor: Simplify job deletion logic by removing user job cleanup from InMemoryJobStore and RedisJobStore * WIP: Add backend inspect script for easier debugging in production * refactor: title generation logic - Changed the title generation endpoint from POST to GET, allowing for more efficient retrieval of titles based on conversation ID. - Implemented exponential backoff for title fetching retries, improving responsiveness and reducing server load. - Introduced a queuing mechanism for title generation, ensuring titles are generated only after job completion. - Updated relevant components and hooks to utilize the new title generation logic, enhancing user experience and application performance. * feat: Enhance updateConvoInAllQueries to support moving conversations to the top * chore: temp. remove added multi convo * refactor: Update active jobs query integration for optimistic updates on abort - Introduced a new interface for active jobs response to standardize data handling. - Updated query keys for active jobs to ensure consistency across components. - Enhanced job management logic in hooks to properly reflect active job states, improving overall application responsiveness. * refactor: useResumableStreamToggle hook to manage resumable streams for legacy/assistants endpoints - Introduced a new hook, useResumableStreamToggle, to automatically toggle resumable streams off for assistants endpoints and restore the previous value when switching away. - Updated ChatView component to utilize the new hook, enhancing the handling of streaming behavior based on endpoint type. - Refactored imports in ChatView for better organization. * refactor: streamline conversation title generation handling - Removed unused type definition for TGenTitleMutation in mutations.ts to clean up the codebase. - Integrated queueTitleGeneration call in useEventHandlers to trigger title generation for new conversations, enhancing the responsiveness of the application. * feat: Add USE_REDIS_STREAMS configuration for stream job storage - Introduced USE_REDIS_STREAMS to control Redis usage for resumable stream job storage, defaulting to true if USE_REDIS is enabled but not explicitly set. - Updated cacheConfig to include USE_REDIS_STREAMS and modified createStreamServices to utilize this new configuration. - Enhanced unit tests to validate the behavior of USE_REDIS_STREAMS under various environment settings, ensuring correct defaults and overrides. * fix: title generation queue management for assistants - Introduced a queueListeners mechanism to notify changes in the title generation queue, improving responsiveness for non-resumable streams. - Updated the useTitleGeneration hook to track queue changes with a queueVersion state, ensuring accurate updates when jobs complete. - Refactored the queueTitleGeneration function to trigger listeners upon adding new conversation IDs, enhancing the overall title generation flow. * refactor: streamline agent controller and remove legacy resumable handling - Updated the AgentController to route all requests to ResumableAgentController, simplifying the logic. - Deprecated the legacy non-resumable path, providing a clear migration path for future use. - Adjusted setHeaders middleware to remove unnecessary checks for resumable mode. - Cleaned up the useResumableSSE hook to eliminate redundant query parameters, enhancing clarity and performance. * feat: Add USE_REDIS_STREAMS configuration to .env.example - Updated .env.example to include USE_REDIS_STREAMS setting, allowing control over Redis usage for resumable LLM streams. - Provided additional context on the behavior of USE_REDIS_STREAMS when not explicitly set, enhancing clarity for configuration management. * refactor: remove unused setHeaders middleware from chat route - Eliminated the setHeaders middleware from the chat route, streamlining the request handling process. - This change contributes to cleaner code and improved performance by reducing unnecessary middleware checks. * fix: Add streamId parameter for resumable stream handling across services (actions, mcp oauth) * fix(flow): add immediate abort handling and fix intervalId initialization - Add immediate abort handler that responds instantly to abort signal - Declare intervalId before cleanup function to prevent 'Cannot access before initialization' error - Consolidate cleanup logic into single function to avoid duplicate cleanup - Properly remove abort event listener on cleanup * fix(mcp): clean up OAuth flows on abort and simplify flow handling - Add abort handler in reconnectServer to clean up mcp_oauth and mcp_get_tokens flows - Update createAbortHandler to clean up both flow types on tool call abort - Pass abort signal to createFlow in returnOnOAuth path - Simplify handleOAuthRequired to always cancel existing flows and start fresh - This ensures user always gets a new OAuth URL instead of waiting for stale flows * fix(agents): handle 'new' conversationId and improve abort reliability - Treat 'new' as placeholder that needs UUID in request controller - Send JSON response immediately before tool loading for faster SSE connection - Use job's abort controller instead of prelimAbortController - Emit errors to stream if headers already sent - Skip 'new' as valid ID in abort endpoint - Add fallback to find active jobs by userId when conversationId is 'new' * fix(stream): detect early abort and prevent navigation to non-existent conversation - Abort controller on job completion to signal pending operations - Detect early abort (no content, no responseMessageId) in abortJob - Set conversation and responseMessage to null for early aborts - Add earlyAbort flag to final event for frontend detection - Remove unused text field from AbortResult interface - Frontend handles earlyAbort by staying on/navigating to new chat * test(mcp): update test to expect signal parameter in createFlow fix(agents): include 'new' conversationId in newConvo check for title generation When frontend sends 'new' as conversationId, it should still trigger title generation since it's a new conversation. Rename boolean variable for clarity fix(agents): check abort state before completeJob for title generation completeJob now triggers abort signal for cleanup, so we need to capture the abort state beforehand to correctly determine if title generation should run.	2025-12-19 12:14:19 -05:00