Both static and instance fallbacks increased from 4096 to 2,000,000 tokens.
When model isn't in models.json cache (e.g. Grok), it was falling back to
4096 tokens causing severe truncation of file reads.
Reuses AGENT_CONTEXT_WINDOW_FALLBACK env var from Patch 2.
* add API key param to Lemonade LLM Provider and Embedding Provider
* add LEMONADE_LLM_API_KEY to .env.example
* add api key to aibitat provider
* fix api key from being sent to frontend
* fix tooltip id
* add null fallback for `apiKey`
* remove console log
* add missing api keys
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* Add User-Agent header for Anthropic API calls
Passes User-Agent: AnythingLLM/{version} to the Anthropic SDK
so Anthropic can identify traffic from AnythingLLM.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* remove test, simplify header default
* unset change to spread
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* fix: Migrate AzureOpenAI model key from OPEN_MODEL_PREF to prevent the naming collision. No effort necessary from current users.
* test: add backwards compat tests for AzureOpenAI model key migration
* patch missing env example file
* linting
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* add eslint config to server
* add break statements to switch case
* add support for browser globals and turn off empty catch blocks
* disable lines with useless try/catch wrappers
* format
* fix no-undef errors
* disbale lines violating no-unsafe-finally
* ignore syncStaticLists.mjs
* use proper null check for creatorId instead of unreachable nullish coalescing
* remove unneeded typescript eslint comment
* make no-unused-private-class-members a warning
* disable line for no-empty-objects
* add new lint script
* fix no-unused-vars violations
* make no-unsued-vars an error
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* checkpoint
* test MCP and flows
* add native tool call detection back to LMStudio
* add native tool call loops for Ollama
* Add ablity detection to DMR (regex parse)
* bedrock and generic openai with ENV flag
* deepseek native tool calling
* localAI native function
* groq support
* linting, add litellm and OR native tool calling via flag
* add check for timings field on final chunk to override usage data
* refactor: extract llama.cpp timings into reusable private method
Move timings extraction into #extractTimings so it can be shared
by both streaming (handleStream) and non-streaming (getChatCompletion)
code paths.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* lint and cleanup
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* Extract Model Table to component
Add provider icons to header rows and installed models
Light mode supported
Mapping for model name id hints to provider
Update DMR to filter chat models by ability since not available via hub API
* linting + dev
* fix incorrect import
* Improve DMR support
- Autodetect models installed
- Grab all models from hub.docker to show available
- UI to handle render,search, install, and management of models
- Support functionality for chat, stream, and agentic calls
* forgot files
* fix loader circle being too large
fix tooltip width command
adjust location of docker installer open for web platform
* adjust imports
* Refactor LLMPerformanceMonitor to use options object for measureStream parameters
* Refactor invocations of `measureStream` to use options arguments
* Change invocation of `measureStream` in anthropic provider to use options argument
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* add model tag to chatCompletion
* add modelTag `model` to async streaming
keeps default arguments for prompt token calculation where applied via explict arg
* fix HF default arg
* render all performance metrics as available for backward compatibility
add `timestamp` to both sync/async chat methods
* extract metrics string to function
* Refactor Azure OpenAI integration to use OpenAI SDK and the v1 API | Enable streaming for Azure Open AI basic inference provider
* Add info tooltip to inform user about 'Model Type' form field
* Add 'model_type_tooltip' key to multiple language translations
* Validate AZURE_OPENAI_ENDPOINT in provider construction
* remove unused import, update error handler, rescope URL utils
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* Support Gitee AI(LLM Provider)
* refactor(server): 重构 GiteeAI 模型窗口限制功能,暂时将窗口限制硬编码,计划使用外部 API 数据和缓存
* updates for Gitee AI
* use legacy lookup since gitee does not enable getting token context windows
* add more missing records
* reorder imports
---------
Co-authored-by: 方程 <fangcheng@oschina.cn>
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* prompt caching for anthropic llm and agent providers
* add UI for control of ENV
simplify implementation
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* feat: add AWS Bedrock API Key option to settings panel
* feat: Bedrock API key auth method
* fix: hide IAM note when using bedrock api key
* move to camcelCase identifier for bedrock api key use
linting
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* fix: Use eval_duration for output TPS calculations and add as a metric field
* refactor usage of eval_duration from ollama metrics
* move eval_duration to usage
* overwrite duration in ollama provider wip measureAsyncFunction optional param
* allow for overloaded duration in measureAsyncFunction
* simplify flow for duration tracking
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* Reimplement Cohere models
- Redo LLM implementation to grab models from endpoint and pre-filter
- Migrate embedding models to also grab from remote
- Add records for easy context window lookup'
* fix comment
* auto model context limit detection for ollama llm provider
* auto model context limit detection for lmstudio llm provider
* Patch Ollama to function and sync context windows like Foundry
* normalize how model context windows are cached from endpoint service
todo: move this into global utility class with MODEL_MAP
eager load models on boot to pre-cache them
add performance model improvements into ollama agent as well as apply n_ctx
* remove debug log
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
