* refactor: modularize openai llm config logic into new getOpenAILLMConfig function (#9412)
* ✈️ refactor: Migrate Anthropic's getLLMConfig to TypeScript (#9413)
* refactor: move tokens.js over to packages/api and update imports
* refactor: port tokens.js to typescript
* refactor: move helpers.js over to packages/api and update imports
* refactor: port helpers.js to typescript
* refactor: move anthropic/llm.js over to packages/api and update imports
* refactor: port anthropic/llm.js to typescript with supporting types in types/anthropic.ts and updated tests in llm.spec.js
* refactor: move llm.spec.js over to packages/api and update import
* refactor: port llm.spec.js over to typescript
* 📝 Add Prompt Parameter Support for Anthropic Custom Endpoints (#9414)
feat: add anthropic llm config support for openai-like (custom) endpoints
* fix: missed compiler / type issues from addition of getAnthropicLLMConfig
* refactor: update tokens.ts to export constants and functions, enhance type definitions, and adjust default values
* WIP: first pass, decouple `llmConfig` from `configOptions`
* chore: update import path for OpenAI configuration from 'llm' to 'config'
* refactor: enhance type definitions for ThinkingConfig and update modelOptions in AnthropicConfigOptions
* refactor: cleanup type, introduce openai transform from alt provider
* chore: integrate removeNullishValues in Google llmConfig and update OpenAI exports
* chore: bump version of @librechat/api to 1.3.5 in package.json and package-lock.json
* refactor: update customParams type in OpenAIConfigOptions to use TConfig['customParams']
* refactor: enhance transformToOpenAIConfig to include fromEndpoint and improve config extraction
* refactor: conform userId field for anthropic/openai, cleanup anthropic typing
* ci: add backward compatibility tests for getOpenAIConfig with various endpoints and configurations
* ci: replace userId with user in clientOptions for getLLMConfig
* test: add Azure OpenAI endpoint tests for various configurations in getOpenAIConfig
* refactor: defaultHeaders retrieval for prompt caching for anthropic-based custom endpoint (litellm)
* test: add unit tests for getOpenAIConfig with various Anthropic model configurations
* test: enhance Anthropic compatibility tests with addParams and dropParams handling
* chore: update @librechat/agents dependency to version 2.4.78 in package.json and package-lock.json
* chore: update @librechat/agents dependency to version 2.4.79 in package.json and package-lock.json
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: freq. and pres. penalty use camelcase
* ci: OpenAI Configuration Tests
* ci: Enhance OpenAI Configuration Tests with Azure and Custom Endpoint Scenarios
* Added integration tests for OpenAI and Azure configurations simulating various initialization scenarios.
* Updated OpenAIConfigOptions to allow null values for reverseProxyUrl and proxy.
* Improved handling of reasoning parameters in tests for both OpenAI and Azure setups.
* Ensured robust error handling for missing API keys and malformed configurations.
* Optimized performance for large parameter sets in configuration.
* test: Add comprehensive integration tests for Anthropic LLM configuration
* Introduced real usage integration tests for various Anthropic endpoint configurations, including handling of proxy and reverse proxy setups.
* Implemented model-specific scenarios for Claude-3.7 and web search functionality.
* Enhanced error handling for missing user IDs and large parameter sets.
* Validated parameter logic, including default values, boundary conditions, and type handling for numeric and array parameters.
* Ensured proper exclusion of system options from model options and maintained expected behavior across different model variations.
* adding beta header context-1m-2025-08-07 to claude sonnet 4 to increase contact window to 1M tokens
* adding context-1m beta header to test cases
* ci: Update Anthropic `getLLMConfig` tests and headers for model variations
- Refactored test cases to ensure proper handling of model variations for 'claude-sonnet-4'.
- Cleaned up unused mock implementations in tests for better clarity and performance.
* refactor: regex in header retrieval for 'claude-sonnet-4' models
* refactor: default tokens for 'claude-sonnet-4' to `1,000,000`
* refactor: add token value retrieval and pattern matching to model tests
---------
Co-authored-by: Dirk Petersen <no-reply@nowhere.com>
* 🔧 fix: enhance client options handling in AgentClient and set default recursion limit
- Updated the recursion limit to default to 25 if not specified in agentsEConfig.
- Enhanced client options in AgentClient to include model parameters such as apiKey and anthropicApiUrl from agentModelParams.
- Updated requestOptions in the anthropic endpoint to use reverseProxyUrl as anthropicApiUrl.
* Enhance LLM configuration tests with edge case handling
* chore add return type annotation for getCustomEndpointConfig function
* fix: update modelOptions handling to use optional chaining and default to empty object in multiple endpoint initializations
* chore: update @librechat/agents to version 2.4.42
* refactor: streamline agent endpoint configuration and enhance client options handling for title generations
- Introduced a new `getProviderConfig` function to centralize provider configuration logic.
- Updated `AgentClient` to utilize the new provider configuration, improving clarity and maintainability.
- Removed redundant code related to endpoint initialization and model parameter handling.
- Enhanced error logging for missing endpoint configurations.
* fix: add abort handling for image generation and editing in OpenAIImageTools
* ci: enhance getLLMConfig tests to verify fetchOptions and dispatcher properties
* fix: use optional chaining for endpointOption properties in getOptions
* fix: increase title generation timeout from 25s to 45s, pass `endpointOption` to `getOptions`
* fix: update file filtering logic in getToolFilesByIds to ensure text field is properly checked
* fix: add error handling for empty OCR results in uploadMistralOCR and uploadAzureMistralOCR
* fix: enhance error handling in file upload to include 'No OCR result' message
* chore: update error messages in uploadMistralOCR and uploadAzureMistralOCR
* fix: enhance filtering logic in getToolFilesByIds to include context checks for OCR resources to only include files directly attached to agent
---------
Co-authored-by: Matt Burnett <matt.burnett@shopify.com>
* chore: update peer dependency for @librechat/agents to version 2.4.41
* 🔧 chore: proxy handling in OpenAI endpoint to use undici
* 🔧 chore: update @anthropic-ai/sdk to version 0.52.0 and refactor proxy handling to use undici
* 🔧 chore: update globIgnores in vite.config.ts to exclude index.html from caching
* 🔧 ci: update proxy handling in getLLMConfig to use fetchOptions and ProxyAgent
* 🔧 chore: refactor proxy handling in Anthropic and OpenAI clients to use fetchOptions
* refactor: agent initialization to streamline model parameters and resendFiles handling
* chore: update @google/generative-ai to version 0.24.0
* fix: handling of top_k and top_p parameters for Claude-3.7 models (allowed without reasoning)
* feat: bump @librechat/agents for Anthropic Reasoning support
* fix: update reasoning handling for OpenRouter integration
* fix: enhance agent token spending logic to include cache creation and read details
* fix: update logic for thinking status in ContentParts component
* refactor: improve agent title handling
* chore: bump @librechat/agents to version 2.1.7 for parallel tool calling for Google models
* chore: include all assets for service worker, remove unused tsconfig.node.json, eslint ignore vite config
* chore: exclude image files from service worker caching
* refactor: simplify googleSchema transformation and error handling
* fix: max output tokens cap for 3.7 models
* fix: skip index fixing in CI, development, and test environments
* ci: add maxOutputTokens handling tests for Claude models
* refactor: drop top_k and top_p parameters for claude-3.7 in AnthropicClient and add tests for new behavior
* refactor: conditionally include top_k and top_p parameters for non-claude-3.7 models
* ci: add unit tests for getLLMConfig function with various model options
* chore: remove all OPENROUTER_API_KEY legacy logic
* refactor: optimize stream chunk handling
* feat: reset model parameters button
* refactor: remove unused examples field from convoSchema and presetSchema
* chore: update librechat-data-provider version to 0.7.6993
* refactor: move excludedKeys set to data-provider for better reusability
* feat: enhance saveMessageToDatabase to handle unset fields and fetched conversation state
* feat: add 'iconURL' and 'greeting' to excludedKeys in data provider config
* fix: add optional chaining to user ID retrieval in getConvo call
