mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-04-02 05:47:19 +02:00
51 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.
|
||
|
Danny Avila
|
f9060fa25f
|
🔧 chore: Update ESLint Config & Run Linter (#10986) | ||
|
Danny Avila
|
656e1abaea
|
🪦 refactor: Remove Legacy Code (#10533)
* 🗑️ chore: Remove unused Legacy Provider clients and related helpers * Deleted OpenAIClient and GoogleClient files along with their associated tests. * Removed references to these clients in the clients index file. * Cleaned up typedefs by removing the OpenAISpecClient export. * Updated chat controllers to use the OpenAI SDK directly instead of the removed client classes. * chore/remove-openapi-specs * 🗑️ chore: Remove unused mergeSort and misc utility functions * Deleted mergeSort.js and misc.js files as they are no longer needed. * Removed references to cleanUpPrimaryKeyValue in messages.js and adjusted related logic. * Updated mongoMeili.ts to eliminate local implementations of removed functions. * chore: remove legacy endpoints * chore: remove all plugins endpoint related code * chore: remove unused prompt handling code and clean up imports * Deleted handleInputs.js and instructions.js files as they are no longer needed. * Removed references to these files in the prompts index.js. * Updated docker-compose.yml to simplify reverse proxy configuration. * chore: remove unused LightningIcon import from Icons.tsx * chore: clean up translation.json by removing deprecated and unused keys * chore: update Jest configuration and remove unused mock file * Simplified the setupFiles array in jest.config.js by removing the fetchEventSource mock. * Deleted the fetchEventSource.js mock file as it is no longer needed. * fix: simplify endpoint type check in Landing and ConversationStarters components * Updated the endpoint type check to use strict equality for better clarity and performance. * Ensured consistency in the handling of the azureOpenAI endpoint across both components. * chore: remove unused dependencies from package.json and package-lock.json * chore: remove legacy EditController, associated routes and imports * chore: update banResponse logic to refine request handling for banned users * chore: remove unused validateEndpoint middleware and its references * chore: remove unused 'res' parameter from initializeClient in multiple endpoint files * chore: remove unused 'isSmallScreen' prop from BookmarkNav and NewChat components; clean up imports in ArchivedChatsTable and useSetIndexOptions hooks; enhance localization in PromptVersions * chore: remove unused import of Constants and TMessage from MobileNav; retain only necessary QueryKeys import * chore: remove unused TResPlugin type and related references; clean up imports in types and schemas |
||
|
Danny Avila
|
c0cb48256e
|
🤖 refactor: Improve Agent Handoff Context Tracking (#10553)
* chore: update @librechat/agents dependency to version 3.0.18 * refactor: add optional metadata field to message schema and types * chore: update @librechat/agents to v3.0.19 * refactor: update return type of sendCompletion method to include metadata * chore: linting * chore: update @librechat/agents dependency to v3.0.20 * refactor: implement agent labeling for conversation history in multi-agent scenarios * refactor: improve error handling for capturing agent ID map in AgentClient * refactor: clear agentIdMap and related properties during client disposal to prevent memory leaks * chore: update sendCompletion method for FakeClient to return an object with completion and metadata fields |
||
|
Danny Avila
|
667e78c51e
|
📦 chore: Remove @langchain/community & Related Legacy Code (#10375)
* chore: remove `@langchain/community` dependency * refactor: remove SerpAPI integration and update related imports * chore: remove legacy code with unnecessary dependencies * chore: cleanup packages * chore: cleanup packages * chore: update openai dependency version to 5.10.1 * chore: add back @librechat/agents dependency * chore: downgrade openai dependency from 5.10.1 to 5.8.2 * Remove dependency on @librechat/agents from the API package * chore: add @librechat/agents dependency to the API package * fix: add useLegacyContent property to RunAgent type and propagate it in createRun function * chore: remove openai dependency version 5.10.1 from package.json |
||
|
Danny Avila
|
8a4a5a4790
|
🤖 feat: Agent Handoffs (Routing) (#10176)
* feat: Add support for agent handoffs with edges in agent forms and schemas chore: Mark `agent_ids` field as deprecated in favor of edges across various schemas and types chore: Update dependencies for @langchain/core and @librechat/agents to latest versions chore: Update peer dependency for @librechat/agents to version 3.0.0-rc2 in package.json chore: Update @librechat/agents dependency to version 3.0.0-rc3 in package.json and package-lock.json feat: first pass, multi-agent handoffs fix: update output type to ToolMessage in memory handling functions fix: improve type checking for graphConfig in createRun function refactor: remove unused content filtering logic in AgentClient chore: update @librechat/agents dependency to version 3.0.0-rc4 in package.json and package-lock.json fix: update @langchain/core peer dependency version to ^0.3.72 in package.json and package-lock.json fix: update @librechat/agents dependency to version 3.0.0-rc6 in package.json and package-lock.json; refactor stream rate handling in various endpoints feat: Agent handoff UI chore: update @librechat/agents dependency to version 3.0.0-rc8 in package.json and package-lock.json fix: improve hasInfo condition and adjust UI element classes in AgentHandoff component refactor: remove current fixed agent display from AgentHandoffs component due to redundancy feat: enhance AgentHandoffs UI with localized beta label and improved layout chore: update @librechat/agents dependency to version 3.0.0-rc10 in package.json and package-lock.json feat: add `createSequentialChainEdges` function to add back agent chaining via multi-agents feat: update `createSequentialChainEdges` call to only provide conversation context between agents feat: deprecate Agent Chain functionality and update related methods for improved clarity * chore: update @librechat/agents dependency to version 3.0.0-rc11 in package.json and package-lock.json * refactor: remove unused addCacheControl function and related imports and import from @librechat/agents * chore: remove unused i18n keys * refactor: remove unused format export from index.ts * chore: update @librechat/agents to v3.0.0-rc13 * chore: remove BEDROCK_LEGACY provider from Providers enum * chore: update @librechat/agents to version 3.0.2 in package.json |
||
|
Sebastien Bruel
|
7c9a868d34
|
📝 feat: Add Markdown Rendering Support for Artifacts (#10049)
* Add Markdown rendering support for artifacts * Add tests * Remove custom code for mermaid * Remove unnecessary dark mode hook * refactor: optimize mermaid dependencies - Added support for additional MIME types in artifact templates. - Updated mermaidDependencies to include new packages: class-variance-authority, clsx, tailwind-merge, and @radix-ui/react-slot. - Refactored zoom and refresh icons in MermaidDiagram component for improved clarity and maintainability. * fix: add Markdown support for artifacts rendering * feat: support 'text/md' as an additional MIME type for Markdown artifacts * refactor: simplify markdownDependencies structure in artifacts utility --------- Co-authored-by: Danny Avila <danny@librechat.ai> |
||
|
Danny Avila
|
48f6f8f2f8
|
📎 feat: Upload as Text Support for Plaintext, STT, RAG, and Token Limits (#8868)
* 🪶 feat: Add Support for Uploading Plaintext Files feat: delineate between OCR and text handling in fileConfig field of config file - also adds support for passing in mimetypes as just plain file extensions feat: add showLabel bool to support future synthetic component DynamicDropdownInput feat: add new combination dropdown-input component in params panel to support file type token limits refactor: move hovercard to side to align with other hovercards chore: clean up autogenerated comments feat: add delineation to file upload path between text and ocr configured filetypes feat: add token limit checks during file upload refactor: move textParsing out of ocrEnabled logic refactor: clean up types for filetype config refactor: finish decoupling DynamicDropdownInput from fileTokenLimits fix: move image token cost function into file to fix circular dependency causing unittest to fail and remove unused var for linter chore: remove out of scope code following review refactor: make fileTokenLimit conform to existing styles chore: remove unused localization string chore: undo changes to DynamicInput and other strays feat: add fileTokenLimit to all provider config panels fix: move textParsing back into ocr tool_resource block for now so that it doesn't interfere with other upload types * 📤 feat: Add RAG API Endpoint Support for Text Parsing (#8849) * feat: implement RAG API integration for text parsing with fallback to native parsing * chore: remove TODO now that placeholder and fllback are implemented * ✈️ refactor: Migrate Text Parsing to TS (#8892) * refactor: move generateShortLivedToken to packages/api * refactor: move textParsing logic into packages/api * refactor: reduce nesting and dry code with createTextFile * fix: add proper source handling * fix: mock new parseText and parseTextNative functions in jest file * ci: add test coverage for textParser * 💬 feat: Add Audio File Support to Upload as Text (#8893) * feat: add STT support for Upload as Text * refactor: move processAudioFile to packages/api * refactor: move textParsing from utils to files * fix: remove audio/mp3 from unsupported mimetypes test since it is now supported * ✂️ feat: Configurable File Token Limits and Truncation (#8911) * feat: add configurable fileTokenLimit default value * fix: add stt to fileConfig merge logic * fix: add fileTokenLimit to mergeFileConfig logic so configurable value is actually respected from yaml * feat: add token limiting to parsed text files * fix: add extraction logic and update tests so fileTokenLimit isnt sent to LLM providers * fix: address comments * refactor: rename textTokenLimiter.ts to text.ts * chore: update form-data package to address CVE-2025-7783 and update package-lock * feat: use default supported mime types for ocr on frontend file validation * fix: should be using logger.debug not console.debug * fix: mock existsSync in text.spec.ts * fix: mock logger rather than every one of its function calls * fix: reorganize imports and streamline file upload processing logic * refactor: update createTextFile function to use destructured parameters and improve readability * chore: update file validation to use EToolResources for improved type safety * chore: update import path for types in audio processing module * fix: update file configuration access and replace console.debug with logger.debug for improved logging --------- Co-authored-by: Dustin Healy <dustinhealy1@gmail.com> Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com> |
||
|
Danny Avila
|
445e9eae85
|
🧩 fix: Human Message Content Handling for Legacy Content (#8525)
* wip: first pass content strings * 📦 chore: update @langchain/core to v0.3.62 for data-provider dev dep. * 📦 chore: bump @langchain/core to v0.3.62 for api dep. * 📦 chore: move @langchain/core to peerDependencies in package.json and package-lock.json * fix: update formatContentStrings to create HumanMessage directly from formatted content * chore: import order |
||
|
Danny Avila
|
452151e408
|
🐛 fix: RAG API failing with OPENID_REUSE_TOKENS Enabled (#8090)
* feat: Implement Short-Lived JWT Token Generation for RAG API * fix: Update import paths * fix: Correct environment variable names for OpenID on behalf flow * fix: Remove unnecessary spaces in OpenID on behalf flow userinfo scope --------- Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com> |
||
|
Danny Avila
|
01e9b196bc
|
🤖 feat: Streamline Endpoints to Agent Framework (#8013)
* refactor(buildEndpointOption): Improve error logging in middleware, consolidate `isAgents` builder logic, remove adding `modelsConfig` to `endpointOption`
* refactor: parameter extraction and organization in agent services, minimize redundancy of shared fields across objects, make clear distinction of parameters processed uniquely by LibreChat vs LLM Provider Configs
* refactor(createPayload): streamline all endpoints to agent route
* fix: add `modelLabel` to response sender options for agent initialization
* chore: correct log message context in EditController abort controller cleanup
* chore: remove unused abortRequest hook
* chore: remove unused addToCache module and its dependencies
* refactor: remove AskController and related routes, update endpoint URLs (now all streamlined to agents route)
* chore: remove unused bedrock route and its related imports
* refactor: simplify response sender logic for Google endpoint
* chore: add `modelDisplayLabel` handling for agents endpoint
* feat: add file search capability to ephemeral agents, update code interpreter selection based of file upload, consolidate main upload menu for all endpoints
* feat: implement useToolToggle hook for managing tool toggle state, refactor CodeInterpreter and WebSearch components to utilize new hook
* feat: add ToolsDropdown component to BadgeRow for enhanced tool options
* feat: introduce BadgeRowContext and BadgeRowProvider for managing conversation state, refactor related components to utilize context
* feat: implement useMCPSelect hook for managing MCP selection state, refactor MCPSelect component to utilize new hook
* feat: enhance BadgeRowContext with MCPSelect and tool toggle functionality, refactor related components to utilize updated context and hooks
* refactor: streamline useToolToggle hook by integrating setEphemeralAgent directly into toggle logic and removing redundant setValue function
* refactor: consolidate codeApiKeyForm and searchApiKeyForm from CodeInterpreter and WebSearch to utilize new context properties
* refactor: update CheckboxButton to support controlled state and enhance ToolsDropdown with permission-based toggles for web search and code interpreter
* refactor: conditionally render CheckboxButton in CodeInterpreter and WebSearch components for improved UI responsiveness
* chore: add jotai dependency to package.json and package-lock.json
* chore: update brace-expansion package to version 2.0.2 in package-lock.json due to CVE-2025-5889
* Revert "chore: add jotai dependency to package.json and package-lock.json"
This reverts commit
|
||
|
Danny Avila
|
d6a17784dc
|
🔗 feat: Agent Chain (Mixture-of-Agents) (#6374)
* wip: first pass, dropdown for selecting sequential agents * refactor: Improve agent selection logic and enhance performance in SequentialAgents component * wip: seq. agents working ideas * wip: sequential agents style change * refactor: move agent form options/submission outside of AgentConfig * refactor: prevent repeating code * refactor: simplify current agent display in SequentialAgents component * feat: persist form value handling in AgentSelect component for agent_ids * feat: first pass, sequential agnets agent update * feat: enhance message display with agent updates and empty text handling * chore: update Icon component to use EModelEndpoint for agent endpoints * feat: update content type checks in BaseClient to use constants for better readability * feat: adjust max context tokens calculation to use 90% of the model's max tokens * feat: first pass, agent run message pruning * chore: increase max listeners for abort controller to prevent memory leaks * feat: enhance runAgent function to include current index count map for improved token tracking * chore: update @librechat/agents dependency to version 2.2.5 * feat: update icons and style of SequentialAgents component for improved UI consistency * feat: add AdvancedButton and AdvancedPanel components for enhanced agent settings navigation, update styling for agent form * chore: adjust minimum height of AdvancedPanel component for better layout consistency * chore: update @librechat/agents dependency to version 2.2.6 * feat: enhance message formatting by incorporating tool set into agent message processing, in order to allow better mix/matching of agents (as tool calls for tools not found in set will be stringified) * refactor: reorder components in AgentConfig for improved readability and maintainability * refactor: enhance layout of AgentUpdate component for improved visual structure * feat: add DeepSeek provider to Bedrock settings and schemas * feat: enhance link styling in mobile.css for better visibility and accessibility * fix: update banner model import in update banner script; export Banner model * refactor: `duplicateAgentHandler` to include tool_resources only for OCR context files * feat: add 'qwen-vl' to visionModels for enhanced model support * fix: change image format from JPEG to PNG in DALLE3 response * feat: reorganize Advanced components and add localizations * refactor: simplify JSX structure in AgentChain component to defer container styling to parent * feat: add FormInput component for reusable input handling * feat: make agent recursion limit configurable from builder * feat: add support for agent capabilities chain in AdvancedPanel and update data-provider version * feat: add maxRecursionLimit configuration for agents and update related documentation * fix: update CONFIG_VERSION to 1.2.3 in data provider configuration * feat: replace recursion limit input with MaxAgentSteps component and enhance input handling * feat: enhance AgentChain component with hover card for additional information and update related labels * fix: pass request and response objects to `createActionTool` when using assistant actions to prevent auth error * feat: update AgentChain component layout to include agent count display * feat: increase default max listeners and implement capability check function for agent chain * fix: update link styles in mobile.css for better visibility in dark mode * chore: temp. remove agents package while bumping shared packages * chore: update @langchain/google-genai package to version 0.1.11 * chore: update @langchain/google-vertexai package to version 0.2.2 * chore: add @librechat/agents package at version 2.2.8 * feat: add deepseek.r1 model with token rate and context values for bedrock |
||
|
Danny Avila
|
d6ab769b80
|
⚠️ refactor: Use Error Content Part Instead Of Throwing Error for Agents (#6262) | ||
|
Danny Avila
|
e14df5956a
|
✨ feat: Anthropic Agents Prompt Caching & UI Accessibility Enhancements (#6045)
* chore: remove auto-focus for now * refactor: move react-hook-form Controller Logic to AgentSelect from AgentPanel * fix: a11y focus issue with AgentSelect by never replacing it in its component tree * fix: maintain ComboBox focus and force re-render on agent ID change in AgentPanel * chore: `gemini-2.0-flash-lite-preview-02-05` (deprecated) * refactor: extract cache control logic and headers configuration to helper functions in AnthropicClient * feat: anthropic agents prompt caching * chore: bump @librechat/agents and related dependencies * fix: typo |
||
|
Danny Avila
|
350e72dede
|
🧠 feat: Reasoning UI for Agents (#5904)
* chore: bump https-proxy-agent and @librechat/agents * refactor: Improve error logging in OllamaClient for API fetch failures * feat: Add DeepSeek provider support and enhance provider name handling * refactor: Use Providers.OLLAMA constant for model name check in fetchModels function * feat: Enhance formatAgentMessages to handle reasoning content type * feat: OpenRouter Agent Reasoning * hard work and dedicationgit add .env.example :) * fix: Handle Google social login with missing last name Social login with Google was previously displaying 'undefined' when a user's last name was empty or not provided. Changes: - Conditionally render last name only if it exists - Prevent displaying 'undefined' when last name is missing * fix: add missing file endings for developers yml,yaml and log --------- Co-authored-by: Mohamed Al-Duraji <mbalduraji@college.harvard.edu> Co-authored-by: Deepak Kendole <deepakdpk101@gmail.com> Co-authored-by: Peter Rothlaender <peter.rothlaender@ginkgo.com> |
||
|
Danny Avila
|
352565c9a6
|
🎥 feat: YouTube Tool (#5582)
* adding youtube tool * refactor: use short `url` param instead of `videoUrl` * refactor: move API key retrieval to a separate credentials module * refactor: remove unnecessary `isEdited` message property * refactor: remove unnecessary `isEdited` message property pt. 2 * refactor: YouTube Tool with new `tool()` generator, handle tools already created by new `tool` generator * fix: only reset request data for multi-convo messages * refactor: enhance YouTube tool by adding transcript parsing and returning structured JSON responses * refactor: update transcript parsing to handle raw response and clean up text output * feat: support toolkits and refactor YouTube tool as a toolkit for better LLM usage * refactor: remove unused OpenAPI specs and streamline tools transformation in loadAsyncEndpoints * refactor: implement manifestToolMap for better tool management and streamline authentication handling * feat: support toolkits for assistants * refactor: rename loadedTools to toolDefinitions for clarity in PluginController and assistant controllers * feat: complete support of toolkits for assistants --------- Co-authored-by: Danilo Pejakovic <danilo.pejakovic@leoninestudios.com> |
||
|
Danny Avila
|
b35a8b78e2
|
🔧 refactor: Improve Agent Context & Minor Fixes (#5349)
* refactor: Improve Context for Agents
* 🔧 fix: Safeguard against undefined properties in OpenAIClient response handling
* refactor: log error before re-throwing for original stack trace
* refactor: remove toolResource state from useFileHandling, allow svg files
* refactor: prevent verbose logs from axios errors when using actions
* refactor: add silent method recordTokenUsage in AgentClient
* refactor: streamline token count assignment in BaseClient
* refactor: enhance safety settings handling for Gemini 2.0 model
* fix: capabilities structure in MCPConnection
* refactor: simplify civic integrity threshold handling in GoogleClient and llm
* refactor: update token count retrieval method in BaseClient tests
* ci: fix test for svg
|
||
|
Danny Avila
|
1a815f5e19
|
🎉 feat: Code Interpreter API and Agents Release (#4860)
* feat: Code Interpreter API & File Search Agent Uploads chore: add back code files wip: first pass, abstract key dialog refactor: influence checkbox on key changes refactor: update localization keys for 'execute code' to 'run code' wip: run code button refactor: add throwError parameter to loadAuthValues and getUserPluginAuthValue functions feat: first pass, API tool calling fix: handle missing toolId in callTool function and return 404 for non-existent tools feat: show code outputs fix: improve error handling in callTool function and log errors fix: handle potential null value for filepath in attachment destructuring fix: normalize language before rendering and prevent null return fix: add loading indicator in RunCode component while executing code feat: add support for conditional code execution in Markdown components feat: attachments refactor: remove bash fix: pass abort signal to graph/run refactor: debounce and rate limit tool call refactor: increase debounce delay for execute function feat: set code output attachments feat: image attachments refactor: apply message context refactor: pass `partIndex` feat: toolCall schema/model/methods feat: block indexing feat: get tool calls chore: imports chore: typing chore: condense type imports feat: get tool calls fix: block indexing chore: typing refactor: update tool calls mapping to support multiple results fix: add unique key to nav link for rendering wip: first pass, tool call results refactor: update query cache from successful tool call mutation style: improve result switcher styling chore: note on using \`.toObject()\` feat: add agent_id field to conversation schema chore: typing refactor: rename agentMap to agentsMap for consistency feat: Agent Name as chat input placeholder chore: bump agents 📦 chore: update @langchain dependencies to latest versions to match agents package 📦 chore: update @librechat/agents dependency to version 1.8.0 fix: Aborting agent stream removes sender; fix(bedrock): completion removes preset name label refactor: remove direct file parameter to use req.file, add `processAgentFileUpload` for image uploads feat: upload menu feat: prime message_file resources feat: implement conversation access validation in chat route refactor: remove file parameter from processFileUpload and use req.file instead feat: add savedMessageIds set to track saved message IDs in BaseClient, to prevent unnecessary double-write to db feat: prevent duplicate message saves by checking savedMessageIds in AgentController refactor: skip legacy RAG API handling for agents feat: add files field to convoSchema refactor: update request type annotations from Express.Request to ServerRequest in file processing functions feat: track conversation files fix: resendFiles, addPreviousAttachments handling feat: add ID validation for session_id and file_id in download route feat: entity_id for code file uploads/downloads fix: code file edge cases feat: delete related tool calls feat: add stream rate handling for LLM configuration feat: enhance system content with attached file information fix: improve error logging in resource priming function * WIP: PoC, sequential agents WIP: PoC Sequential Agents, first pass content data + bump agents package fix: package-lock WIP: PoC, o1 support, refactor bufferString feat: convertJsonSchemaToZod fix: form issues and schema defining erroneous model fix: max length issue on agent form instructions, limit conversation messages to sequential agents feat: add abort signal support to createRun function and AgentClient feat: PoC, hide prior sequential agent steps fix: update parameter naming from config to metadata in event handlers for clarity, add model to usage data refactor: use only last contentData, track model for usage data chore: bump agents package fix: content parts issue refactor: filter contentParts to include tool calls and relevant indices feat: show function calls refactor: filter context messages to exclude tool calls when no tools are available to the agent fix: ensure tool call content is not undefined in formatMessages feat: add agent_id field to conversationPreset schema feat: hide sequential agents feat: increase upload toast duration to 10 seconds * refactor: tool context handling & update Code API Key Dialog feat: toolContextMap chore: skipSpecs -> useSpecs ci: fix handleTools tests feat: API Key Dialog * feat: Agent Permissions Admin Controls feat: replace label with button for prompt permission toggle feat: update agent permissions feat: enable experimental agents and streamline capability configuration feat: implement access control for agents and enhance endpoint menu items feat: add welcome message for agent selection in localization feat: add agents permission to access control and update version to 0.7.57 * fix: update types in useAssistantListMap and useMentions hooks for better null handling * feat: mention agents * fix: agent tool resource race conditions when deleting agent tool resource files * feat: add error handling for code execution with user feedback * refactor: rename AdminControls to AdminSettings for clarity * style: add gap to button in AdminSettings for improved layout * refactor: separate agent query hooks and check access to enable fetching * fix: remove unused provider from agent initialization options, creates issue with custom endpoints * refactor: remove redundant/deprecated modelOptions from AgentClient processes * chore: update @librechat/agents to version 1.8.5 in package.json and package-lock.json * fix: minor styling issues + agent panel uniformity * fix: agent edge cases when set endpoint is no longer defined * refactor: remove unused cleanup function call from AppService * fix: update link in ApiKeyDialog to point to pricing page * fix: improve type handling and layout calculations in SidePanel component * fix: add missing localization string for agent selection in SidePanel * chore: form styling and localizations for upload filesearch/code interpreter * fix: model selection placeholder logic in AgentConfig component * style: agent capabilities * fix: add localization for provider selection and improve dropdown styling in ModelPanel * refactor: use gpt-4o-mini > gpt-3.5-turbo * fix: agents configuration for loadDefaultInterface and update related tests * feat: DALLE Agents support |
||
|
Danny Avila
|
95201908e9
|
📦 fix: npm warnings; chore: bump deprecated packages (#4707)
* chore: bump langchain deps to address vulnerability warnings * chore: bump community package and install textsplitters package * fix: update expected result in tokenSplit tests for accuracy * chore: remove CodeSherpa tools * chore: remove E2B tools and loadToolSuite * chore: remove CodeBrew tool and update related references * chore: remove HumanTool and ChatTool, update tool references * chore: remove Zapier tool from manifest.json and update SerpAPI * chore: remove basic tools * chore: update import path for RecursiveCharacterTextSplitter * chore: update import path for DynamicStructuredTool * chore: remove extractionChain.js and update tool filtering logic * chore: npm audit fix * chore: bump google packages * chore: update DALL-E tool to DALL-E-3 and adjust authentication logic * ci: update message classes * chore: elliptic npm audit fix * chore: update CallbackManager import and remove deprecated tool handling logic * chore: imports order * chore: remove unused code --------- Co-authored-by: Max Sanna <max@maxsanna.com> |
||
|
Danny Avila
|
766643ea1c
|
🎯 feat: Enhance Title Parameter Parsing with new Anthropic Format | ||
|
Danny Avila
|
0c2a583df8
|
🔧 refactor: Optimize Agent Tool Loading and Fix Bedrock Tool Handling (#4641)
* fix: bedrock tool name regex * fix: pass args as single input, attempt json first. * refactor: remove toolMap from agent tool load as is not used * fix: update formatAgentMessages test to use strictEqual for args comparison, testing new behavior |
||
|
Danny Avila
|
2e519f9b57
|
🤖 feat: Custom Endpoint Agents (experimental) (#4627)
* wip: first pass, custom endpoint agents * chore: imports * chore: consolidate exports * fix: imports * feat: convert message.content array to strings for legacy format handling (deepseek/groq) * refactor: normalize ollama endpoint name * refactor: update mocking in isDomainAllowed.spec.js * refactor: update deepseekModels in tokens.js and tokens.spec.js |
||
|
Danny Avila
|
ad74350036
|
🚧 chore: merge latest dev build (#4288)
* fix: agent initialization, add `collectedUsage` handling * style: improve side panel styling * refactor(loadAgent): Optimize order agent project ID retrieval * feat: code execution * fix: typing issues * feat: ExecuteCode content part * refactor: use local state for default collapsed state of analysis content parts * fix: code parsing in ExecuteCode component * chore: bump agents package, export loadAuthValues * refactor: Update handleTools.js to use EnvVar for code execution tool authentication * WIP * feat: download code outputs * fix(useEventHandlers): type issues * feat: backend handling for code outputs * Refactor: Remove console.log statement in Part.tsx * refactor: add attachments to TMessage/messageSchema * WIP: prelim handling for code outputs * feat: attachments rendering * refactor: improve attachments rendering * fix: attachments, nullish edge case, handle attachments from event stream, bump agents package * fix filename download * fix: tool assignment for 'run code' on agent creation * fix: image handling by adding attachments * refactor: prevent agent creation without provider/model * refactor: remove unnecessary space in agent creation success message * refactor: select first model if selecting provider from empty on form * fix: Agent avatar bug * fix: `defaultAgentFormValues` causing boolean typing issue and typeerror * fix: capabilities counting as tools, causing duplication of them * fix: formatted messages edge case where consecutive content text type parts with the latter having tool_call_ids would cause consecutive AI messages to be created. furthermore, content could not be an array for tool_use messages (anthropic limitation) * chore: bump @librechat/agents dependency to version 1.6.9 * feat: bedrock agents * feat: new Agents icon * feat: agent titling * feat: agent landing * refactor: allow sharing agent globally only if user is admin or author * feat: initial AgentPanelSkeleton * feat: AgentPanelSkeleton * feat: collaborative agents * chore: add potential authorName as part of schema * chore: Remove unnecessary console.log statement * WIP: agent model parameters * chore: ToolsDialog typing and tool related localization chnages * refactor: update tool instance type (latest langchain class), and rename google tool to 'google' proper * chore: add back tools * feat: Agent knowledge files upload * refactor: better verbiage for disabled knowledge * chore: debug logs for file deletions * chore: debug logs for file deletions * feat: upload/delete agent knowledge/file-search files * feat: file search UI for agents * feat: first pass, file search tool * chore: update default agent capabilities and info |
||
|
Danny Avila
|
9a393be012
|
🪨 fix: Formatting Edge Case Handling for Bedrock Messages (#4016)
* refactor: Remove console.log statement in SelectDropDown component * fix(bedrock): edge case - message.content as string creating message formatting issue |
||
|
Danny Avila
|
d59b62174f
|
🪨 feat: AWS Bedrock support (#3935)
* feat: Add BedrockIcon component to SVG library * feat: EModelEndpoint.bedrock * feat: first pass, bedrock chat. note: AgentClient is returning `agents` as conversation.endpoint * fix: declare endpoint in initialization step * chore: Update @librechat/agents dependency to version 1.4.5 * feat: backend content aggregation for agents/bedrock * feat: abort agent requests * feat: AWS Bedrock icons * WIP: agent provider schema parsing * chore: Update EditIcon props type * refactor(useGenerationsByLatest): make agents and bedrock editable * refactor: non-assistant message content, parts * fix: Bedrock response `sender` * fix: use endpointOption.model_parameters not endpointOption.modelOptions * fix: types for step handler * refactor: Update Agents.ToolCallDelta type * refactor: Remove unnecessary assignment of parentMessageId in AskController * refactor: remove unnecessary assignment of parentMessageId (agent request handler) * fix(bedrock/agents): message regeneration * refactor: dynamic form elements using react-hook-form Controllers * fix: agent icons/labels for messages * fix: agent actions * fix: use of new dynamic tags causing application crash * refactor: dynamic settings touch-ups * refactor: update Slider component to allow custom track class name * refactor: update DynamicSlider component styles * refactor: use Constants value for GLOBAL_PROJECT_NAME (enum) * feat: agent share global methods/controllers * fix: agents query * fix: `getResponseModel` * fix: share prompt a11y issue * refactor: update SharePrompt dialog theme styles * refactor: explicit typing for SharePrompt * feat: add agent roles/permissions * chore: update @librechat/agents dependency to version 1.4.7 for tool_call_ids edge case * fix(Anthropic): messages.X.content.Y.tool_use.input: Input should be a valid dictionary * fix: handle text parts with tool_call_ids and empty text * fix: role initialization * refactor: don't make instructions required * refactor: improve typing of Text part * fix: setShowStopButton for agents route * chore: remove params for now * fix: add streamBuffer and streamRate to help prevent 'Overloaded' errors from Anthropic API * refactor: remove console.log statement in ContentRender component * chore: typing, rename Context to Delete Button * chore(DeleteButton): logging * refactor(Action): make accessible * style(Action): improve a11y again * refactor: remove use/mention of mongoose sessions * feat: first pass, sharing agents * feat: visual indicator for global agent, remove author when serving to non-author * wip: params * chore: fix typing issues * fix(schemas): typing * refactor: improve accessibility of ListCard component and fix console React warning * wip: reset templates for non-legacy new convos * Revert "wip: params" This reverts commit |
||
|
Danny Avila
|
a0291ed155
|
🚧 chore: merge latest dev build to main repo (#3844)
* agents - phase 1 (#30) * chore: copy assistant files * feat: frontend and data-provider * feat: backend get endpoint test * fix(MessageEndpointIcon): switched to AgentName and AgentAvatar * fix: small fixes * fix: agent endpoint config * fix: show Agent Builder * chore: install agentus * chore: initial scaffolding for agents * fix: updated Assistant logic to Agent Logic for some Agent components * WIP first pass, demo of agent package * WIP: initial backend infra for agents * fix: agent list error * wip: agents routing * chore: Refactor useSSE hook to handle different data events * wip: correctly emit events * chore: Update @librechat/agentus npm dependency to version 1.0.9 * remove comment * first pass: streaming agent text * chore: Remove @librechat/agentus root-level workspace npm dependency * feat: Agent Schema and Model * fix: content handling fixes * fix: content message save * WIP: new content data * fix: run step issue with tool calls * chore: Update @librechat/agentus npm dependency to version 1.1.5 * feat: update controller and agent routes * wip: initial backend tool and tool error handling support * wip: tool chunks * chore: Update @librechat/agentus npm dependency to version 1.1.7 * chore: update tool_call typing, add test conditions and logs * fix: create agent * fix: create agent * first pass: render completed content parts * fix: remove logging, fix step handler typing * chore: Update @librechat/agentus npm dependency to version 1.1.9 * refactor: cleanup maps on unmount * chore: Update BaseClient.js to safely count tokens for string, number, and boolean values * fix: support subsequent messages with tool_calls * chore: export order * fix: select agent * fix: tool call types and handling * chore: switch to anthropic for testing * fix: AgentSelect * refactor: experimental: OpenAIClient to use array for intermediateReply * fix(useSSE): revert old condition for streaming legacy client tokens * fix: lint * revert `agent_id` to `id` * chore: update localization keys for agent-related components * feat: zod schema handling for actions * refactor(actions): if no params, no zodSchema * chore: Update @librechat/agentus npm dependency to version 1.2.1 * feat: first pass, actions * refactor: empty schema for actions without params * feat: Update createRun function to accept additional options * fix: message payload formatting; feat: add more client options * fix: ToolCall component rendering when action has no args but has output * refactor(ToolCall): allow non-stringy args * WIP: first pass, correctly formatted tool_calls between providers * refactor: Remove duplicate import of 'roles' module * refactor: Exclude 'vite.config.ts' from TypeScript compilation * refactor: fix agent related types > - no need to use endpoint/model fields for identifying agent metadata > - add `provider` distinction for agent-configured 'endpoint' - no need for agent-endpoint map - reduce complexity of tools as functions into tools as string[] - fix types related to above changes - reduce unnecessary variables for queries/mutations and corresponding react-query keys * refactor: Add tools and tool_kwargs fields to agent schema * refactor: Remove unused code and update dependencies * refactor: Update updateAgentHandler to use req.body directly * refactor: Update AgentSelect component to use localized hooks * refactor: Update agent schema to include tools and provider fields * refactor(AgentPanel): add scrollbar gutter, add provider field to form, fix agent schema required values * refactor: Update AgentSwitcher component to use selectedAgentId instead of selectedAgent * refactor: Update AgentPanel component to include alternateName import and defaultAgentFormValues * refactor(SelectDropDown): allow setting value as option while still supporting legacy usage (string values only) * refactor: SelectDropdown changes - Only necessary when the available values are objects with label/value fields and the selected value is expected to be a string. * refactor: TypeError issues and handle provider as option * feat: Add placeholder for provider selection in AgentPanel component * refactor: Update agent schema to include author and provider fields * fix: show expected 'create agent' placeholder when creating agent * chore: fix localization strings, hide capabilities form for now * chore: typing * refactor: import order and use compact agents schema for now * chore: typing * refactor: Update AgentForm type to use AgentCapabilities * fix agent form agent selection issues * feat: responsive agent selection * fix: Handle cancelled fetch in useSelectAgent hook * fix: reset agent form on accordion close/open * feat: Add agent_id to default conversation for agents endpoint * feat: agents endpoint request handling * refactor: reset conversation model on agent select * refactor: add `additional_instructions` to conversation schema, organize other fields * chore: casing * chore: types * refactor(loadAgentTools): explicitly pass agent_id, do not pass `model` to loadAgentTools for now, load action sets by agent_id * WIP: initial draft of real agent client initialization * WIP: first pass, anthropic agent requests * feat: remember last selected agent * feat: openai and azure connected * fix: prioritize agent model for runs unless an explicit override model is passed from client * feat: Agent Actions * fix: save agent id to convo * feat: model panel (#29) * feat: model panel * bring back comments * fix: method still null * fix: AgentPanel FormContext * feat: add more parameters * fix: style issues; refactor: Agent Controller * fix: cherry-pick * fix: Update AgentAvatar component to use AssistantIcon instead of BrainCircuit * feat: OGDialog for delete agent; feat(assistant): update Agent types, introduced `model_parameters` * feat: icon and general `model_parameters` update * feat: use react-hook-form better * fix: agent builder form reset issue when switching panels * refactor: modularize agent builder form --------- Co-authored-by: Danny Avila <danny@librechat.ai> * fix: AgentPanel and ModelPanel type issues and use `useFormContext` and `watch` instead of `methods` directly and `useWatch`. * fix: tool call issues due to invalid input (anthropic) of empty string * fix: handle empty text in Part component --------- Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com> * refactor: remove form ModelPanel and fixed nested ternary expressions in AgentConfig * fix: Model Parameters not saved correctly * refactor: remove console log * feat: avatar upload and get for Agents (#36) Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com> * chore: update to public package * fix: typing, optional chaining * fix: cursor not showing for content parts * chore: conditionally enable agents * ci: fix azure test * ci: fix frontend tests, fix eslint api * refactor: Remove unused errorContentPart variable * continue of the agent message PR (#40) * last fixes * fix: agentMap * pr merge test (#41) * fix: model icon not fetching correctly * remove console logs * feat: agent name * refactor: pass documentsMap as a prop to allow re-render of assistant form * refactor: pass documentsMap as a prop to allow re-render of assistant form * chore: Bump version to 0.7.419 * fix: TypeError: Cannot read properties of undefined (reading 'id') * refactor: update AgentSwitcher component to use ControlCombobox instead of Combobox --------- Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com> |
||
|
Danny Avila
|
7c1ee242eb
|
🪄 feat: Code Artifacts (#3798)
* feat: Add CodeArtifacts component to Beta settings tab * chore: Update npm dependency to @codesandbox/sandpack-react@2.18.2 * WIP: artifacts first pass * WIP first pass remark-directive * chore: revert markdown to original component + new artifacts rendering * refactor: first pass rewrite * refactor: add throttling * first pass styling * style: Add Radix Tabs, more styling changes * feat: second pass * style: code styling * fix: package markdown fixes * feat: Add useEffect hook to Artifacts component for visibility control, slide in animation * fix: only set artifact if there is content * refactor: typing and make latest artifact active if the number of artifacts changed * feat: artifacts + shadcnui * feat: Add Copy Code button to Artifacts component * feat: first pass streaming updates * refactor: optimize ordering of artifacts in Artifacts component * refactor: optimize ordering of artifacts and add latest artifact activation in Artifacts component * refactor: add order prop to Artifact * feat: update to latest, use update time for ordering * refactor: optimize ordering of artifacts and activate latest artifact in Artifacts component * wip: remove thinking text and artifact formatting if empty * refactor: optimize Markdown rendering and add support for code artifacts * feat: global state for current artifact Id and set on artifact preview click * refactor: Rename CodePreview component to ArtifactButton * refactor: apply growth to artifact frame so artifact preview can take full space * refactor: remove artifactIdsState * refactor: nullify artifact state and reset on empty conversation * feat: reset artifact state on conversation change * feat: artifacts system prompt in backend * refactor: update UI artifact toggle label to match localization key * style: remove ArtifactButton inline-block styling * feat: memoize ArtifactPreview, add html support * refactor: abstract out components * chore: bump react-resizable-panel * refactor: resizable panel order props * fix: side panel resizing crashes * style: temporarily remove scrolling, add better styling * chore: remove thinking for now * chore: preprocess artifacts for now * feat: Add auto scrolling to CodeMarkdown (artifacts) * feat: autoswitch to preview * feat: auto switch to code, adjust prompt, remove unused code * feat: refresh button * feat: open/close artifacts * wip: mermaid * refactor: w-fit Artifact button * chore: organize code * feat: first pass mermaid * refactor: improve panning logic in MermaidDiagram component * feat: center/zoom on first render * refactor: add centering with reset button * style: mermaid styling * refactor: add back MermaidDiagram * fix: static/html template * fix: mermaid * add examples to artifacts prompt * refactor: fix CodeBar plugin prop logic * refactor: remove unnecessary mention of artifacts when not requested * fix: remove preprocessCodeArtifacts function and fix imports * feat: improve artifacts guidelines and remove unnecessary mentions * refactor: improve artifacts guidelines and remove unnecessary mentions * chore: uninstall unused packages * chore: bump vite * chore: update three dependency to version 0.167.1 * refactor: move beta settings, add additional artifacts toggles * feat: artifacts mode toggles * refactor: adjust prompt * feat: shadcnui instructions * feat: code artifacts custom prompt mode * chore: Update artifacts UI labels and instructions localizations * refactor: Remove unused code in Markdown component |
||
|
Danny Avila
|
8ca1e4f94f
|
🐛 fix: Anthropic Prompt Caching Edge Case (#3690) | ||
|
Danny Avila
|
a45b384bbc
|
💾 feat: Anthropic Prompt Caching (#3670)
* wip: initial cache control implementation, add typing for transactions handling * feat: first pass of Anthropic Prompt Caching * feat: standardize stream usage as pass in when calculating token counts * feat: Add getCacheMultiplier function to calculate cache multiplier for different valueKeys and cacheTypes * chore: imports order * refactor: token usage recording in AnthropicClient, no need to "correct" as we have the correct amount * feat: more accurate token counting using stream usage data * feat: Improve token counting accuracy with stream usage data * refactor: ensure more accurate than not token estimations if custom instructions or files are not being resent with every request * refactor: cleanup updateUserMessageTokenCount to allow transactions to be as accurate as possible even if we shouldn't update user message token counts * ci: fix tests |
||
|
Danny Avila
|
084cf266a2
|
🗃️ fix: revise RAG prompt (#3006) | ||
|
nidasfly
|
795bb9c568
|
🌏 refactor: Improve Title Prompt for Multilingual Titles (#2832) | ||
|
Danny Avila
|
2ec821ea4c
|
🌍 : Updated Translations & AI Generation Scripts (#2666)
* chore: bun scripts * feat: comparisons * refactor: move scripts to own folder * feat: generated prompts script and Es output * feat: generated prompts * created prompts * feat: Russian localization prompts * translation setup * additional ES translations * additional ES translations * translation services * feat: additional translations * fix regex for parseParamPrompt * RU translations * remove stores from git * update gitignore * update gitignore * ZH translations * move gen prompt output location * ZH traditional translations * AR translations * chore: rename * JP * cleanup scripts * add additional instruction prompts * fix translation prompt and add DE * FR translations (rate limited so not complete) * chore: update translation comparisons * chore: remove unused AnthropicClient changes * refactor: use compositional styling for archive/delete buttons, fix manage archive table styling |
||
|
Danny Avila
|
9d854dac07
|
🤖 feat: Gemini 1.5 Support (+Vertex AI) (#2383)
* WIP: gemini-1.5 support * feat: extended vertex ai support * fix: handle possibly undefined modelName * fix: gpt-4-turbo-preview invalid vision model * feat: specify `fileConfig.imageOutputType` and make PNG default image conversion type * feat: better truncation for errors including base64 strings * fix: gemini inlineData formatting * feat: RAG augmented prompt for gemini-1.5 * feat: gemini-1.5 rates and token window * chore: adjust tokens, update docs, update vision Models * chore: add back `ChatGoogleVertexAI` for chat models via vertex ai * refactor: ask/edit controllers to not use `unfinished` field for google endpoint * chore: remove comment * chore(ci): fix AppService test * chore: remove comment * refactor(GoogleSearch): use `GOOGLE_SEARCH_API_KEY` instead, issue warning for old variable * chore: bump data-provider to 0.5.4 * chore: update docs * fix: condition for gemini-1.5 using generative ai lib * chore: update docs * ci: add additional AppService test for `imageOutputType` * refactor: optimize new config value `imageOutputType` * chore: bump CONFIG_VERSION * fix(assistants): avatar upload |
||
|
Danny Avila
|
cd7f3a51e1
|
🧠 feat: Cohere support as Custom Endpoint (#2328)
* chore: bump cohere-ai, fix firebase vulnerabilities by going down versions * feat: cohere rates and context windows * feat(createCoherePayload): transform openai payload for cohere compatibility * feat: cohere backend support * refactor(UnknownIcon): optimize icon render and add cohere * docs: add cohere to Compatible AI Endpoints * Update ai_endpoints.md |
||
|
Danny Avila
|
a00756c469
|
⬇️ feat: Assistant File Downloads (#2234)
* WIP: basic route for file downloads and file strategy for generating readablestream to pipe as res * chore(DALLE3): add typing for OpenAI client * chore: add `CONSOLE_JSON` notes to dotenv.md * WIP: first pass OpenAI Assistants File Output handling * feat: first pass assistants output file download from openai * chore: yml vs. yaml variation to .gitignore for `librechat.yml` * refactor(retrieveAndProcessFile): remove redundancies * fix(syncMessages): explicit sort of apiMessages to fix message order on abort * chore: add logs for warnings and errors, show toast on frontend * chore: add logger where console was still being used |
||
|
Danny Avila
|
798e8763d0
|
👓 feat: Vision Support for Assistants (#2195)
* refactor(assistants/chat): use promises to speed up initialization, initialize shared variables, include `attachedFileIds` to streamRunManager * chore: additional typedefs * fix(OpenAIClient): handle edge case where attachments promise is resolved * feat: createVisionPrompt * feat: Vision Support for Assistants |
||
|
Danny Avila
|
1f0fb497f8
|
🎉 feat: Optimizations and Anthropic Title Generation (#2184)
* feat: add claude-3-haiku-20240307 to default anthropic list * refactor: optimize `saveMessage` calls mid-stream via throttling * chore: remove addMetadata operations and consolidate in BaseClient * fix(listAssistantsForAzure): attempt to specify correct model mapping as accurately as possible (#2177) * refactor(client): update last conversation setup with current assistant model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model * refactor(cache): explicitly add TTL of 2 minutes when setting titleCache and add default TTL of 10 minutes to abortKeys cache * feat(AnthropicClient): conversation titling using Anthropic Function Calling * chore: remove extraneous token usage logging * fix(convos): unhandled edge case for conversation grouping (undefined conversation) * style: Improved style of Search Bar after recent UI update * chore: remove unused code, content part helpers * feat: always show code option |
||
|
Danny Avila
|
45a95acec2
|
📂 feat: RAG Improvements (#2169)
* feat: new vector file processing strategy * chore: remove unused client files * chore: remove more unused client files * chore: remove more unused client files and move used to new dir * chore(DataIcon): add className * WIP: Model Endpoint Settings Update, draft additional context settings * feat: improve parsing for augmented prompt, add full context option * chore: remove volume mounting from rag.yml as no longer necessary |
||
|
Danny Avila
|
f7761df52c
|
🗃️ feat: General File Support for OpenAI, Azure, Custom, Anthropic and Google (RAG) (#2143)
* refactor: re-purpose `resendImages` as `resendFiles` * refactor: re-purpose `resendImages` as `resendFiles` * feat: upload general files * feat: embed file during upload * feat: delete file embeddings on file deletion * chore(fileConfig): add epub+zip type * feat(encodeAndFormat): handle non-image files * feat(createContextHandlers): build context prompt from file attachments and successful RAG * fix: prevent non-temp files as well as embedded files to be deleted on new conversation * fix: remove temp_file_id on usage, prevent non-temp files as well as embedded files to be deleted on new conversation * fix: prevent non-temp files as well as embedded files to be deleted on new conversation * feat(OpenAI/Anthropic/Google): basic RAG support * fix: delete `resendFiles` only when true (Default) * refactor(RAG): update endpoints and pass JWT * fix(resendFiles): default values * fix(context/processFile): query unique ids only * feat: rag-api.yaml * feat: file upload improved ux for longer uploads * chore: await embed call and catch embedding errors * refactor: store augmentedPrompt in Client * refactor(processFileUpload): throw error if not assistant file upload * fix(useFileHandling): handle markdown empty mimetype issue * chore: necessary compose file changes |
||
|
Danny Avila
|
8263ddda3f
|
🤖 feat(Anthropic): Claude 3 & Vision Support (#1984)
* chore: bump anthropic SDK * chore: update anthropic config settings (fileSupport, default models) * feat: anthropic multi modal formatting * refactor: update vision models and use endpoint specific max long side resizing * feat(anthropic): multimodal messages, retry logic, and messages payload * chore: add more safety to trimming content due to whitespace error for assistant messages * feat(anthropic): token accounting and resending multiple images in progress * chore: bump data-provider * feat(anthropic): resendImages feature * chore: optimize Edit/Ask controllers, switch model back to req model * fix: false positive of invalid model * refactor(validateVisionModel): use object as arg, pass in additional/available models * refactor(validateModel): use helper function, `getModelsConfig` * feat: add modelsConfig to endpointOption so it gets passed to all clients, use for properly validating vision models * refactor: initialize default vision model and make sure it's available before assigning it * refactor(useSSE): avoid resetting model if user selected a new model between request and response * feat: show rate in transaction logging * fix: return tokenCountMap regardless of payload shape |
||
|
Danny Avila
|
ecd63eb9f1
|
✨ feat: Assistants API, General File Support, Side Panel, File Explorer (#1696)
* feat: assistant name/icon in Landing & Header * feat: assistname in textarea placeholder, and use `Assistant` as default name * feat: display non-image files in user messages * fix: only render files if files.length is > 0 * refactor(config -> file-config): move file related configuration values to separate module, add excel types * chore: spreadsheet file rendering * fix(Landing): dark mode style for Assistant Name * refactor: move progress incrementing to own hook, start smaller, cap near limit \(1\) * refactor(useContentHandler): add empty Text part if last part was completed tool or image * chore: add accordion trigger border styling for dark mode * feat: Assistant Builder model selection * chore: use Spinner when Assistant is mutating * fix(get/assistants): return correct response object `AssistantListResponse` * refactor(Spinner): pass size as prop * refactor: make assistant crud mutations optimistic, add types for options * chore: remove assistants route and view * chore: move assistant builder components to separate directory * feat(ContextButton): delete Assistant via context button/dialog, add localization * refactor: conditionally show use and context menu buttons, add localization for create assistant * feat: save side panel states to localStorage * style(SidePanel): improve avatar menu and assistant select styling for dark mode * refactor: make NavToggle reusable for either side (left or right), add SidePanel Toggle with ability to close it completely * fix: resize handle and navToggle behavior * fix(/avatar/:assistant_id): await `deleteFile` and assign unique name to uploaded image * WIP: file UI components from PR #576 * refactor(OpenAIMinimalIcon): pass className * feat: formatDate helper fn * feat: DataTableColumnHeader * feat: add row selection, formatted row values, number of rows selected * WIP: add files to Side panel temporarily * feat: `LB_QueueAsyncCall`: Leaky Bucket queue for external APIs, use in `processDeleteRequest` * fix(TFile): correct `source` type with `FileSources` * fix(useFileHandling): use `continue` instead of return when iterating multiple files, add file type to extendedFile * chore: add generic setter type * refactor(processDeleteRequest): settle promises to prevent rejections from processing deletions, log errors * feat: `useFileDeletion` to reuse file deletion logic * refactor(useFileDeletion): make `setFiles` an optional param and use object as param * feat: useDeleteFilesFromTable * feat: use real `files` data and add deletion action to data table * fix(Table): make headers sticky * feat: add dynamic filtering for columns; only show to user Host or OpenAI storage type * style(DropdownMenu): replace `slate` with `gray` * style(DataTable): apply dark mode themes and other misc styling * style(Columns): add color to OpenAI Storage option * refactor(FileContainer): make file preview reusable * refactor(Images): make image preview reusable * refactor(FilePreview): make file prop optional for FileIcon and FilePreview, fix relative style * feat(Columns): add file/image previews, set a minimum size to show for file size in bytes * WIP: File Panel with real files and formatted * feat: open files dialog from panel * style: file data table mobile and general column styling fixes * refactor(api/files): return files sorted by the most recently updated * refactor: provide fileMap through context to prevent re-selecting files to map in different areas; remove unused imports commented out in PanelColumns * refactor(ExtendFile): make File type optional, add `attached` to prevent attached files from being deleted on remove, make Message.files a partial TFile type * feat: attach files through file panel * refactor(useFileHandling): move files to the start of cache list when uploaded * refactor(useDeleteFilesMutation): delete files from cache when successfully deleted from server * fix(FileRow): handle possible edge case of duplication due to attaching recently uploaded file * style(SidePanel): make resize grip border transparent, remove unnecessary styling on close sidepanel button * feat: action utilities and tests * refactor(actions): add `ValidationResult` type and change wording for no server URL found * refactor(actions): check for empty server URL * fix(data-provider): revert tsconfig to fix type issue resolution * feat(client): first pass of actions input for assistants * refactor(FunctionSignature): change method to output object instead of string * refactor(models/Assistant): add actions field to schema, use searchParams object for methods, and add `getAssistant` * feat: post actions input first pass - create new Action document - add actions to Assistant DB document - create /action/:assistant_id POST route - pass more props down from PanelSwitcher, derive assistant_id from switcher - move privacy policy to ActionInput - reset data on input change/validation - add `useUpdateAction` - conform FunctionSignature type to FunctionTool - add action, assistant doc, update hook related types * refactor: optimize assistant/actions relationship - past domain in metadata as hostname and not a URL - include domain in tool name - add `getActions` for actions retrieval by user - add `getAssistants` for assistant docs retrieval by user - add `assistant_id` to Action schema - move actions to own module as a subroute to `api/assistants` - add `useGetActionsQuery` and `useGetAssistantDocsQuery` hooks - fix Action type def * feat: show assistant actions in assistant builder * feat: switch to actions on action click, editing action styling * fix: add Assistant state for builder panel to allow immediate selection of newly created assistants as well as retaining the current assistant when switching to a different panel within the builder * refactor(SidePanel/NavToggle): offset less from right when SidePanel is completely collapsed * chore: rename `processActions` -> `processRequiredActions` * chore: rename Assistant API Action to RequiredAction * refactor(actions): avoid nesting actual API params under generic `requestBody` to optimize LLM token usage * fix(handleTools): avoid calling `validTool` if not defined, add optional param to skip the loading of specs, which throws an error in the context of assistants * WIP: working first pass of toolCalls generated from openapi specs * WIP: first pass ToolCall styling * feat: programmatic iv encryption/decryption helpers * fix: correct ActionAuth types/enums, and define type for AuthForm * feat: encryption/decryption helpers for Action AuthMetadata * refactor(getActions): remove sensitive fields from query response * refactor(POST/actions): encrypt and remove sensitive fields from mutation response * fix(ActionService): change ESM import to CJS * feat: frontend auth handling for actions + optimistic update on action update/creation * refactor(actions): use the correct variables and types for setAuth method * refactor: POST /:assistant_id action can now handle updating an existing action, add `saved_auth_fields` to determine when user explicitly saves new auth creds. only send auth metadata if user explicitly saved fields * refactor(createActionTool): catch errors and send back meaningful error message, add flag to `getActions` to determine whether to retrieve sensitive values or not * refactor(ToolService): add `action` property to ToolCall PartMetadata to determine if the tool call was an action, fix parsing function name issue with actionDelimiter * fix(ActionRequest): use URL class to correctly join endpoint parts for `execute` call * feat: delete assistant actions * refactor: conditionally show Available actions * refactor: show `retrieval` and `code_interpreter` as Capabilities, swap `Switch` for `Checkbox` * chore: remove shadow-stroke from messages * WIP: first pass of Assistants Knowledge attachments * refactor: remove AssistantsProvider in favor of FormProvider, fix selectedAssistant re-render bug, map Assistant file_ids to files via fileMap, initialize Knowledge component with mapped files if any exist * fix: prevent deleting files on assistant file upload * chore: remove console.log * refactor(useUploadFileMutation): update files and assistants cache on upload * chore: disable oauth option as not supported yet * feat: cancel assistant runs * refactor: initialize OpenAI client with helper function, resolve all related circular dependencies * fix(DALL-E): initialization * fix(process): openai client initialization * fix: select an existing Assistant when the active one is deleted * chore: allow attaching files for assistant endpoint, send back relevant OpenAI error message when uploading, deconstruct openAI initialization correctly, add `message_file` to formData when a file is attached to the message but not the assistant * fix: add assistant_id on newConvo * fix(initializeClient): import fix * chore: swap setAssistant for setOption in useEffect * fix(DALL-E): add processFileURL to loadTools call * chore: add customConfig to debug logs * feat: delete threads on convo delete * chore: replace Assistants icon * chore: remove console.dir() in `abortRun` * feat(AssistantService): accumulate text values from run in openai.responseText * feat: titling for assistants endpoint * chore: move panel file components to appropriate directory, add file checks for attaching files, change icon for Attach Files * refactor: add localizations to tools, plugins, add condition for adding/remove user plugins so tool selections don't affect this value * chore: disable `import from url` action for now * chore: remove textMimeTypes from default fileConfig for now * fix: catch tool errors and send as outputs with error messages * fix: React warning about button as descendant of button * style: retrieval and cancelled icon * WIP: pass isSubmitting to Parts, use InProgressCall to display cancelled tool calls correctly, show domain/function name * fix(meilisearch): fix `postSaveHook` issue where indexing expects a mongo document, and join all text content parts for meili indexing * ci: fix dall-e tests * ci: fix client tests * fix: button types in actions panel * fix: plugin auth form persisting across tool selections * fix(ci): update AppService spec with `loadAndFormatTools` * fix(clearConvos): add id check earlier on * refactor(AssistantAvatar): set previewURL dynamically when emtadata.avatar changes * feat(assistants): addTitle cache setting * fix(useSSE): resolve rebase conflicts * fix: delete mutation * style(SidePanel): make grip visible on active and hover, invisible otherwise * ci: add data-provider tests to workflow, also update eslint/tsconfig to recognize specs, and add `text/csv` to fileConfig * fix: handle edge case where auth object is undefined, and log errors * refactor(actions): resolve schemas, add tests for resolving refs, import specs from separate file for tests * chore: remove comment * fix(ActionsInput): re-render bug when initializing states with action fields * fix(patch/assistant): filter undefined tools * chore: add logging for errors in assistants routes * fix(updateAssistant): map actions to functions to avoid overwriting * fix(actions): properly handle GET paths * fix(convos): unhandled delete thread exception * refactor(AssistantService): pass both thread_id and conversationId when sending intermediate assistant messages, remove `mapMessagesToSteps` from AssistantService * refactor(useSSE): replace all messages with runMessages and pass latestMessageId to abortRun; fix(checkMessageGaps): include tool calls when syncing messages * refactor(assistants/chat): invoke `createOnTextProgress` after thread creation * chore: add typing * style: sidepanel styling * style: action tool call domain styling * feat(assistants): default models, limit retrieval to certain models, add env variables to to env.example * feat: assistants api key in EndpointService * refactor: set assistant model to conversation on assistant switch * refactor: set assistant model to conversation on assistant select from panel * fix(retrieveAndProcessFile): catch attempt to download file with `assistant` purpose which is not allowed; add logging * feat: retrieval styling, handling, and logging * chore: rename ASSISTANTS_REVERSE_PROXY to ASSISTANTS_BASE_URL * feat: FileContext for file metadata * feat: context file mgmt and filtering * style(Select): hover/rounded changes * refactor: explicit conversation switch, endpoint dependent, through `useSelectAssistant`, which does not create new chat if current endpoint is assistant endpoint * fix(AssistantAvatar): make empty previewURL if no avatar present * refactor: side panel mobile styling * style: merge tool and action section, optimize mobile styling for action/tool buttons * fix: localStorage issues * fix(useSelectAssistant): invoke react query hook directly in select hook as Map was not being updated in time * style: light mode fixes * fix: prevent sidepanel nav styling from shifting layout up * refactor: change default layout (collapsed by default) * style: mobile optimization of DataTable * style: datatable * feat: client-side hide right-side panel * chore(useNewConvo): add partial typing for preset * fix(useSelectAssistant): pass correct model name by using template as preset * WIP: assistant presets * refactor(ToolService): add native solution for `TavilySearchResults` and log tool output errors * refactor: organize imports and use native TavilySearchResults * fix(TavilySearchResults): stringify result * fix(ToolCall): show tool call outputs when not an action * chore: rename Prompt Prefix to custom instructions (in user facing text only) * refactor(EditPresetDialog): Optimize setting title by debouncing, reset preset on dialog close to avoid state mixture * feat: add `presetOverride` to overwrite active conversation settings when saving a Preset (relevant for client side updates only) * feat: Assistant preset settings (client-side) * fix(Switcher): only set assistant_id and model if current endpoint is Assistants * feat: use `useDebouncedInput` for updating conversation settings, starting with EditPresetDialog title setting and Assistant instructions setting * feat(Assistants): add instructions field to settings * feat(chat/assistants): pass conversation settings to run body * wip: begin localization and only allow actions if the assistant is created * refactor(AssistantsPanel): knowledge localization, allow tools on creation * feat: experimental: allow 'priming' values before assistant is created, that would normally require an assistant_id to be defined * chore: trim console logs and make more meaningful * chore: toast messages * fix(ci): date test * feat: create file when uploading Assistant Avatar * feat: file upload rate limiting from custom config with dynamic file route initialization * refactor: use file upload limiters on post routes only * refactor(fileConfig): add endpoints field for endpoint specific fileconfigs, add mergeConfig function, add tests * refactor: fileConfig route, dynamic multer instances used on all '/' and '/images' POST routes, data service and query hook * feat: supportedMimeTypesSchema, test for array of regex * feat: configurable file config limits * chore: clarify assistants file knowledge prereq. * chore(useTextarea): default to localized 'Assistant' if assistant name is empty * feat: configurable file limits and toggle file upload per endpoint * fix(useUploadFileMutation): prevent updating assistant.files cache if file upload is a message_file attachment * fix(AssistantSelect): set last selected assistant only when timeout successfully runs * refactor(queries): disable assistant queries if assistants endpoint is not enabled * chore(Switcher): add localization * chore: pluralize `assistant` for `EModelEndpoint key and value * feat: show/hide assistant UI components based on endpoint availability; librechat.yaml config for disabling builder section and setting polling/timeout intervals * fix(compactEndpointSchemas): use EModelEndpoint for schema access * feat(runAssistant): use configured values from `librechat.yaml` for `pollIntervalMs` and `timeout` * fix: naming issue * wip: revert landing * 🎉 happy birthday LibreChat (#1768) * happy birthday LibreChat * Refactor endpoint condition in Landing component * Update birthday message in Eng.tsx * fix(/config): avoid nesting ternaries * refactor(/config): check birthday --------- Co-authored-by: Danny Avila <messagedaniel@protonmail.com> * fix: landing * fix: landing * fix(useMessageHelpers): hardcoded check to use EModelEndpoint instead * fix(ci): convo test revert to main * fix(assistants/chat): fix issue where assistant_id was being saved as model for convo * chore: added logging, promises racing to prevent longer timeouts, explicit setting of maxRetries and timeouts, robust catching of invalid abortRun params * refactor: use recoil state for `showStopButton` and only show for assistants endpoint after syncing conversation data * refactor: optimize abortRun strategy using localStorage, refactor `abortConversation` to use async/await and await the result, refactor how the abortKey cache is set for runs * fix(checkMessageGaps): assign `assistant_id` to synced messages if defined; prevents UI from showing blank assistant for cancelled messages * refactor: re-order sequence of chat route, only allow aborting messages after run is created, cancel abortRun if there was a cancelling error (likely due already cancelled in chat route), and add extra logging * chore(typedefs): add httpAgent type to OpenAIClient * refactor: use custom implementation of retrieving run with axios to allow for timing out run query * fix(waitForRun): handle timed out run retrieval query * refactor: update preset conditions: - presets will retain settings when a different endpoint is selected; for existing convos, either when modular or is assistant switch - no longer use `navigateToConvo` on preset select * fix: temporary calculator hack as expects string input when invoked * fix: cancel abortRun only when cancelling error is a result of the run already being cancelled * chore: remove use of `fileMaxSizeMB` and total counterpart (redundant) * docs: custom config documentation update * docs: assistants api setup and dotenv, new custom config fields * refactor(Switcher): make Assistant switcher sticky in SidePanel * chore(useSSE): remove console log of data and message index * refactor(AssistantPanel): button styling and add secondary select button to bottom of panel * refactor(OpenAIClient): allow passing conversationId to RunManager through titleConvo and initializeLLM to properly record title context tokens used in cases where conversationId was not defined by the client * feat(assistants): token tracking for assistant runs * chore(spendTokens): improve logging * feat: support/exclude specific assistant Ids * chore: add update `librechat.example.yaml`, optimize `AppService` handling, new tests for `AppService`, optimize missing/outdate config logging * chore: mount docker logs to root of project * chore: condense axios errors * chore: bump vite * chore: vite hot reload fix using latest version * chore(getOpenAIModels): sort instruct models to the end of models list * fix(assistants): user provided key * fix(assistants): user provided key, invalidate more queries on revoke --------- Co-authored-by: Marco Beretta <81851188+Berry-13@users.noreply.github.com> |
||
|
Danny Avila
|
379e470e38
|
🧹fix: Handle Abort Message Edge Cases (#1462)
* chore: bump langchain to v0.0.213 from v0.0.186 * fix: handle abort edge cases: - abort message server-side if response experienced error mid-generation - attempt to recover message if aborting resulted in error - if abortKey is not provided, use conversationId if it exists - if headers were already sent, send an Event stream message - issue warning for possible Google censor/filter refactor(streamResponse): for `sendError`, allow passing overrides so that error can include partial generation, improve typing for `sendMessage` * chore(MessageContent): remove eslint warning for unused `i`, rephrase unfinished message text * fix(useSSE): avoid invoking cancelHandler if the abort response was 404 * chore(TMessage): remove unnecessary, unused legacy message property `submitting` * chore(TMessage): remove unnecessary legacy message property `cancelled` * chore(abortMiddleware): remove unused `errorText` property to avoid confusion |
||
|
Danny Avila
|
583e978a82
|
feat(Google): Support all Text/Chat Models, Response streaming, PaLM -> Google 🤖 (#1316)
* feat: update PaLM icons * feat: add additional google models * POC: formatting inputs for Vertex AI streaming * refactor: move endpoints services outside of /routes dir to /services/Endpoints * refactor: shorten schemas import * refactor: rename PALM to GOOGLE * feat: make Google editable endpoint * feat: reusable Ask and Edit controllers based off Anthropic * chore: organize imports/logic * fix(parseConvo): include examples in googleSchema * fix: google only allows odd number of messages to be sent * fix: pass proxy to AnthropicClient * refactor: change `google` altName to `Google` * refactor: update getModelMaxTokens and related functions to handle maxTokensMap with nested endpoint model key/values * refactor: google Icon and response sender changes (Codey and Google logo instead of PaLM in all cases) * feat: google support for maxTokensMap * feat: google updated endpoints with Ask/Edit controllers, buildOptions, and initializeClient * feat(GoogleClient): now builds prompt for text models and supports real streaming from Vertex AI through langchain * chore(GoogleClient): remove comments, left before for reference in git history * docs: update google instructions (WIP) * docs(apis_and_tokens.md): add images to google instructions * docs: remove typo apis_and_tokens.md * Update apis_and_tokens.md * feat(Google): use default settings map, fully support context for both text and chat models, fully support examples for chat models * chore: update more PaLM references to Google * chore: move playwright out of workflows to avoid failing tests |
||
|
Danny Avila
|
317cdd3f77
|
feat: Vision Support + New UI (#1203)
* feat: add timer duration to showToast, show toast for preset selection * refactor: replace old /chat/ route with /c/. e2e tests will fail here * refactor: move typedefs to root of /api/ and add a few to assistant types in TS * refactor: reorganize data-provider imports, fix dependency cycle, strategize new plan to separate react dependent packages * feat: add dataService for uploading images * feat(data-provider): add mutation keys * feat: file resizing and upload * WIP: initial API image handling * fix: catch JSON.parse of localStorage tools * chore: experimental: use module-alias for absolute imports * refactor: change temp_file_id strategy * fix: updating files state by using Map and defining react query callbacks in a way that keeps them during component unmount, initial delete handling * feat: properly handle file deletion * refactor: unexpose complete filepath and resize from server for higher fidelity * fix: make sure resized height, width is saved, catch bad requests * refactor: use absolute imports * fix: prevent setOptions from being called more than once for OpenAIClient, made note to fix for PluginsClient * refactor: import supportsFiles and models vars from schemas * fix: correctly replace temp file id * refactor(BaseClient): use absolute imports, pass message 'opts' to buildMessages method, count tokens for nested objects/arrays * feat: add validateVisionModel to determine if model has vision capabilities * chore(checkBalance): update jsdoc * feat: formatVisionMessage: change message content format dependent on role and image_urls passed * refactor: add usage to File schema, make create and updateFile, correctly set and remove TTL * feat: working vision support TODO: file size, type, amount validations, making sure they are styled right, and making sure you can add images from the clipboard/dragging * feat: clipboard support for uploading images * feat: handle files on drop to screen, refactor top level view code to Presentation component so the useDragHelpers hook has ChatContext * fix(Images): replace uploaded images in place * feat: add filepath validation to protect sensitive files * fix: ensure correct file_ids are push and not the Map key values * fix(ToastContext): type issue * feat: add basic file validation * fix(useDragHelpers): correct context issue with `files` dependency * refactor: consolidate setErrors logic to setError * feat: add dialog Image overlay on image click * fix: close endpoints menu on click * chore: set detail to auto, make note for configuration * fix: react warning (button desc. of button) * refactor: optimize filepath handling, pass file_ids to images for easier re-use * refactor: optimize image file handling, allow re-using files in regen, pass more file metadata in messages * feat: lazy loading images including use of upload preview * fix: SetKeyDialog closing, stopPropagation on Dialog content click * style(EndpointMenuItem): tighten up the style, fix dark theme showing in lightmode, make menu more ux friendly * style: change maxheight of all settings textareas to 138px from 300px * style: better styling for textarea and enclosing buttons * refactor(PresetItems): swap back edit and delete icons * feat: make textarea placeholder dynamic to endpoint * style: show user hover buttons only on hover when message is streaming * fix: ordered list not going past 9, fix css * feat: add User/AI labels; style: hide loading spinner * feat: add back custom footer, change original footer text * feat: dynamic landing icons based on endpoint * chore: comment out assistants route * fix: autoScroll to newest on /c/ view * fix: Export Conversation on new UI * style: match message style of official more closely * ci: fix api jest unit tests, comment out e2e tests for now as they will fail until addressed * feat: more file validation and use blob in preview field, not filepath, to fix temp deletion * feat: filefilter for multer * feat: better AI labels based on custom name, model, and endpoint instead of `ChatGPT` |
||
|
Danny Avila
|
abbc57a49a
|
fix(formatMessages): Conform Name Property to OpenAI Expected Regex (#1076)
* fix(formatMessages): conform name property to OpenAI expected regex * fix(ci): prior test was expecting non-sanitized name input |
||
|
Danny Avila
|
365c39c405
|
feat: Accurate Token Usage Tracking & Optional Balance (#1018)
* refactor(Chains/llms): allow passing callbacks * refactor(BaseClient): accurately count completion tokens as generation only * refactor(OpenAIClient): remove unused getTokenCountForResponse, pass streaming var and callbacks in initializeLLM * wip: summary prompt tokens * refactor(summarizeMessages): new cut-off strategy that generates a better summary by adding context from beginning, truncating the middle, and providing the end wip: draft out relevant providers and variables for token tracing * refactor(createLLM): make streaming prop false by default * chore: remove use of getTokenCountForResponse * refactor(agents): use BufferMemory as ConversationSummaryBufferMemory token usage not easy to trace * chore: remove passing of streaming prop, also console log useful vars for tracing * feat: formatFromLangChain helper function to count tokens for ChatModelStart * refactor(initializeLLM): add role for LLM tracing * chore(formatFromLangChain): update JSDoc * feat(formatMessages): formats langChain messages into OpenAI payload format * chore: install openai-chat-tokens * refactor(formatMessage): optimize conditional langChain logic fix(formatFromLangChain): fix destructuring * feat: accurate prompt tokens for ChatModelStart before generation * refactor(handleChatModelStart): move to callbacks dir, use factory function * refactor(initializeLLM): rename 'role' to 'context' * feat(Balance/Transaction): new schema/models for tracking token spend refactor(Key): factor out model export to separate file * refactor(initializeClient): add req,res objects to client options * feat: add-balance script to add to an existing users' token balance refactor(Transaction): use multiplier map/function, return balance update * refactor(Tx): update enum for tokenType, return 1 for multiplier if no map match * refactor(Tx): add fair fallback value multiplier incase the config result is undefined * refactor(Balance): rename 'tokens' to 'tokenCredits' * feat: balance check, add tx.js for new tx-related methods and tests * chore(summaryPrompts): update prompt token count * refactor(callbacks): pass req, res wip: check balance * refactor(Tx): make convoId a String type, fix(calculateTokenValue) * refactor(BaseClient): add conversationId as client prop when assigned * feat(RunManager): track LLM runs with manager, track token spend from LLM, refactor(OpenAIClient): use RunManager to create callbacks, pass user prop to langchain api calls * feat(spendTokens): helper to spend prompt/completion tokens * feat(checkBalance): add helper to check, log, deny request if balance doesn't have enough funds refactor(Balance): static check method to return object instead of boolean now wip(OpenAIClient): implement use of checkBalance * refactor(initializeLLM): add token buffer to assure summary isn't generated when subsequent payload is too large refactor(OpenAIClient): add checkBalance refactor(createStartHandler): add checkBalance * chore: remove prompt and completion token logging from route handler * chore(spendTokens): add JSDoc * feat(logTokenCost): record transactions for basic api calls * chore(ask/edit): invoke getResponseSender only once per API call * refactor(ask/edit): pass promptTokens to getIds and include in abort data * refactor(getIds -> getReqData): rename function * refactor(Tx): increase value if incomplete message * feat: record tokenUsage when message is aborted * refactor: subtract tokens when payload includes function_call * refactor: add namespace for token_balance * fix(spendTokens): only execute if corresponding token type amounts are defined * refactor(checkBalance): throws Error if not enough token credits * refactor(runTitleChain): pass and use signal, spread object props in create helpers, and use 'call' instead of 'run' * fix(abortMiddleware): circular dependency, and default to empty string for completionTokens * fix: properly cancel title requests when there isn't enough tokens to generate * feat(predictNewSummary): custom chain for summaries to allow signal passing refactor(summaryBuffer): use new custom chain * feat(RunManager): add getRunByConversationId method, refactor: remove run and throw llm error on handleLLMError * refactor(createStartHandler): if summary, add error details to runs * fix(OpenAIClient): support aborting from summarization & showing error to user refactor(summarizeMessages): remove unnecessary operations counting summaryPromptTokens and note for alternative, pass signal to summaryBuffer * refactor(logTokenCost -> recordTokenUsage): rename * refactor(checkBalance): include promptTokens in errorMessage * refactor(checkBalance/spendTokens): move to models dir * fix(createLanguageChain): correctly pass config * refactor(initializeLLM/title): add tokenBuffer of 150 for balance check * refactor(openAPIPlugin): pass signal and memory, filter functions by the one being called * refactor(createStartHandler): add error to run if context is plugins as well * refactor(RunManager/handleLLMError): throw error immediately if plugins, don't remove run * refactor(PluginsClient): pass memory and signal to tools, cleanup error handling logic * chore: use absolute equality for addTitle condition * refactor(checkBalance): move checkBalance to execute after userMessage and tokenCounts are saved, also make conditional * style: icon changes to match official * fix(BaseClient): getTokenCountForResponse -> getTokenCount * fix(formatLangChainMessages): add kwargs as fallback prop from lc_kwargs, update JSDoc * refactor(Tx.create): does not update balance if CHECK_BALANCE is not enabled * fix(e2e/cleanUp): cleanup new collections, import all model methods from index * fix(config/add-balance): add uncaughtException listener * fix: circular dependency * refactor(initializeLLM/checkBalance): append new generations to errorMessage if cost exceeds balance * fix(handleResponseMessage): only record token usage in this method if not error and completion is not skipped * fix(createStartHandler): correct condition for generations * chore: bump postcss due to moderate severity vulnerability * chore: bump zod due to low severity vulnerability * chore: bump openai & data-provider version * feat(types): OpenAI Message types * chore: update bun lockfile * refactor(CodeBlock): add error block formatting * refactor(utils/Plugin): factor out formatJSON and cn to separate files (json.ts and cn.ts), add extractJSON * chore(logViolation): delete user_id after error is logged * refactor(getMessageError -> Error): change to React.FC, add token_balance handling, use extractJSON to determine JSON instead of regex * fix(DALL-E): use latest openai SDK * chore: reorganize imports, fix type issue * feat(server): add balance route * fix(api/models): add auth * feat(data-provider): /api/balance query * feat: show balance if checking is enabled, refetch on final message or error * chore: update docs, .env.example with token_usage info, add balance script command * fix(Balance): fallback to empty obj for balance query * style: slight adjustment of balance element * docs(token_usage): add PR notes |
||
|
Danny Avila
|
317a1bd8da
|
feat: ConversationSummaryBufferMemory (#973)
* refactor: pass model in message edit payload, use encoder in standalone util function * feat: add summaryBuffer helper * refactor(api/messages): use new countTokens helper and add auth middleware at top * wip: ConversationSummaryBufferMemory * refactor: move pre-generation helpers to prompts dir * chore: remove console log * chore: remove test as payload will no longer carry tokenCount * chore: update getMessagesWithinTokenLimit JSDoc * refactor: optimize getMessagesForConversation and also break on summary, feat(ci): getMessagesForConversation tests * refactor(getMessagesForConvo): count '00000000-0000-0000-0000-000000000000' as root message * chore: add newer model to token map * fix: condition was point to prop of array instead of message prop * refactor(BaseClient): use object for refineMessages param, rename 'summary' to 'summaryMessage', add previous_summary refactor(getMessagesWithinTokenLimit): replace text and tokenCount if should summarize, summary, and summaryTokenCount are present fix/refactor(handleContextStrategy): use the right comparison length for context diff, and replace payload first message when a summary is present * chore: log previous_summary if debugging * refactor(formatMessage): assume if role is defined that it's a valid value * refactor(getMessagesWithinTokenLimit): remove summary logic refactor(handleContextStrategy): add usePrevSummary logic in case only summary was pruned refactor(loadHistory): initial message query will return all ordered messages but keep track of the latest summary refactor(getMessagesForConversation): use object for single param, edit jsdoc, edit all files using the method refactor(ChatGPTClient): order messages before buildPrompt is called, TODO: add convoSumBuffMemory logic * fix: undefined handling and summarizing only when shouldRefineContext is true * chore(BaseClient): fix test results omitting system role for summaries and test edge case * chore: export summaryBuffer from index file * refactor(OpenAIClient/BaseClient): move refineMessages to subclass, implement LLM initialization for summaryBuffer * feat: add OPENAI_SUMMARIZE to enable summarizing, refactor: rename client prop 'shouldRefineContext' to 'shouldSummarize', change contextStrategy value to 'summarize' from 'refine' * refactor: rename refineMessages method to summarizeMessages for clarity * chore: clarify summary future intent in .env.example * refactor(initializeLLM): handle case for either 'model' or 'modelName' being passed * feat(gptPlugins): enable summarization for plugins * refactor(gptPlugins): utilize new initializeLLM method and formatting methods for messages, use payload array for currentMessages and assign pastMessages sooner * refactor(agents): use ConversationSummaryBufferMemory for both agent types * refactor(formatMessage): optimize original method for langchain, add helper function for langchain messages, add JSDocs and tests * refactor(summaryBuffer): add helper to createSummaryBufferMemory, and use new formatting helpers * fix: forgot to spread formatMessages also took opportunity to pluralize filename * refactor: pass memory to tools, namely openapi specs. not used and may never be used by new method but added for testing * ci(formatMessages): add more exhaustive checks for langchain messages * feat: add debug env var for OpenAI * chore: delete unnecessary comments * chore: add extra note about summary feature * fix: remove tokenCount from payload instructions * fix: test fail * fix: only pass instructions to payload when defined or not empty object * refactor: fromPromptMessages is deprecated, use renamed method fromMessages * refactor: use 'includes' instead of 'startsWith' for extended OpenRouter compatibility * fix(PluginsClient.buildPromptBody): handle undefined message strings * chore: log langchain titling error * feat: getModelMaxTokens helper * feat: tokenSplit helper * feat: summary prompts updated * fix: optimize _CUT_OFF_SUMMARIZER prompt * refactor(summaryBuffer): use custom summary prompt, allow prompt to be passed, pass humanPrefix and aiPrefix to memory, along with any future variables, rename messagesToRefine to context * fix(summaryBuffer): handle edge case where messagesToRefine exceeds summary context, refactor(BaseClient): allow custom maxContextTokens to be passed to getMessagesWithinTokenLimit, add defined check before unshifting summaryMessage, update shouldSummarize based on this refactor(OpenAIClient): use getModelMaxTokens, use cut-off message method for summary if no messages were left after pruning * fix(handleContextStrategy): handle case where incoming prompt is bigger than model context * chore: rename refinedContent to splitText * chore: remove unnecessary debug log |
||
|
Danny Avila
|
1d3e336e1c
|
feat: Add Option to Disable Titling, Config Titling Model, and Title Prompt Improvements (#977)
* feat: add option to disable titling as well as decide what model to use for OpenAI titling refactor: truncate conversation text so it caps around 200 tokens for titling requests, optimize some of the title prompts * feat: disable bing titling with TITLE_CONVO as well |
||
|
Danny Avila
|
4ca43fb53d
|
refactor: Encrypt & Expire User Provided Keys, feat: Rate Limiting (#874)
* docs: make_your_own.md formatting fix for mkdocs * feat: add express-mongo-sanitize feat: add login/registration rate limiting * chore: remove unnecessary console log * wip: remove token handling from localStorage to encrypted DB solution * refactor: minor change to UserService * fix mongo query and add keys route to server * fix backend controllers and simplify schema/crud * refactor: rename token to key to separate from access/refresh tokens, setTokenDialog -> setKeyDialog * refactor(schemas): TEndpointOption token -> key * refactor(api): use new encrypted key retrieval system * fix(SetKeyDialog): fix key prop error * fix(abortMiddleware): pass random UUID if messageId is not generated yet for proper error display on frontend * fix(getUserKey): wrong prop passed in arg, adds error handling * fix: prevent message without conversationId from saving to DB, prevents branching on the frontend to a new top-level branch * refactor: change wording of multiple display messages * refactor(checkExpiry -> checkUserKeyExpiry): move to UserService file * fix: type imports from common * refactor(SubmitButton): convert to TS * refactor(key.ts): change localStorage map key name * refactor: add new custom tailwind classes to better match openAI colors * chore: remove unnecessary warning and catch ScreenShot error * refactor: move userKey frontend logic to hooks and remove use of localStorage and instead query the DB * refactor: invalidate correct query key, memoize userKey hook, conditionally render SetKeyDialog to avoid unnecessary calls, refactor SubmitButton props and useEffect for showing 'provide key first' * fix(SetKeyDialog): use enum-like object for expiry values feat(Dropdown): add optionsClassName to dynamically change dropdown options container classes * fix: handle edge case where user had provided a key but the server changes to env variable for keys * refactor(OpenAI/titleConvo): move titling to client to retain authorized credentials in message lifecycle for titling * fix(azure): handle user_provided keys correctly for azure * feat: send user Id to OpenAI to differentiate users in completion requests * refactor(OpenAI/titleConvo): adding tokens helps minimize LLM from using the language in title response * feat: add delete endpoint for keys * chore: remove throttling of title * feat: add 'Data controls' to Settings, add 'Revoke' keys feature in Key Dialog and Data controls * refactor: reorganize PluginsClient files in langchain format * feat: use langchain for titling convos * chore: cleanup titling convo, with fallback to original method, escape braces, use only snippet for language detection * refactor: move helper functions to appropriate langchain folders for reusability * fix: userProvidesKey handling for gptPlugins * fix: frontend handling of plugins key * chore: cleanup logging and ts-ignore SSE * fix: forwardRef misuse in DangerButton * fix(GoogleConfig/FileUpload): localize errors and simplify validation with zod * fix: cleanup google logging and fix user provided key handling * chore: remove titling from google * chore: removing logging from browser endpoint * wip: fix menu flicker * feat: useLocalStorage hook * feat: add Tooltip for UI * refactor(EndpointMenu): utilize Tooltip and useLocalStorage, remove old 'New Chat' slide-over * fix(e2e): use testId for endpoint menu trigger * chore: final touches to EndpointMenu before future refactor to declutter component * refactor(localization): change select endpoint to open menu and add translations * chore: add final prop to error message response * ci: minor edits to facilitate testing * ci: new e2e test which tests for new key setting/revoking features |
||
|
Danny Avila
|
e5336039fc
|
ci(backend-review.yml): add linter step to the backend review workflow (#625)
* ci(backend-review.yml): add linter step to the backend review workflow * chore(backend-review.yml): remove prettier from lint-action configuration * chore: apply new linting workflow * chore(lint-staged.config.js): reorder lint-staged tasks for JavaScript and TypeScript files * chore(eslint): update ignorePatterns in .eslintrc.js chore(lint-action): remove prettier option in backend-review.yml chore(package.json): add lint and lint:fix scripts * chore(lint-staged.config.js): remove prettier --write command for js, jsx, ts, tsx files * chore(titleConvo.js): remove unnecessary console.log statement chore(titleConvo.js): add missing comma in options object * chore: apply linting to all files * chore(lint-staged.config.js): update lint-staged configuration to include prettier formatting |