flowstate-dojo-community-epicdm-flowstate-agents-llm-client

Use this skill when a task touches packages/flowstate-agents-llm-client, imports @epicdm/flowstate-agents-llm-client, or needs to teach humans/agents how this package works.

Package identity:

• Package: @epicdm/flowstate-agents-llm-client
• Repository: epic-flowstate-community
• Version authority: package.json (1.0.7)
• Dojo course: flowstate-dojo-community-epicdm-flowstate-agents-llm-client

How to use the package:

• Purpose: Unified LLM API client for Epic Flow with multi-provider support
• Start with package-local docs when present.
• Verify details against source and tests before changing behavior.
• Use the Dojo course lessons as the teaching path: setup, mental model, core workflow, integration, feature labs, maintenance.

Public surfaces discovered:

• LLMClient
• anthropicConfig
• lmstudioConfig
• openaiConfig
• providerRegistry
• getProviderConfig
• ModelConfig
• ProviderConfig
• createLLMProxy
• LLMProvider
• LLMClientConfig
• RetryConfig
• LoggingConfig
• Logger
• BudgetConfig
• AMSConfig
• KnowledgeStoreConfig
• QueryParams
• ToolDefinition
• LLMRequest
• LLMResponse
• LLMErrorCode
• LLMError
• LLMResult
• TokenUsage
• CostBreakdown
• ToolCall
• ResultMetadata
• StreamChunk
• TextDeltaChunk

Composable feature skilllets:

• Anthropic Config: use feature labs for workflow, source anchor, and regression risk.
• Calculate Cost: use feature labs for workflow, source anchor, and regression risk.
• Create LLMProxy: use feature labs for workflow, source anchor, and regression risk.
• Create Logger: use feature labs for workflow, source anchor, and regression risk.
• Detect Environment: use feature labs for workflow, source anchor, and regression risk.
• Get Provider Config: use feature labs for workflow, source anchor, and regression risk.
• LLMClient: use feature labs for workflow, source anchor, and regression risk.
• LLMError: use feature labs for workflow, source anchor, and regression risk.
• LLMError Code: use feature labs for workflow, source anchor, and regression risk.
• Lmstudio Config: use feature labs for workflow, source anchor, and regression risk.
• Openai Config: use feature labs for workflow, source anchor, and regression risk.
• Provider Registry: use feature labs for workflow, source anchor, and regression risk.
• With Retry: use feature labs for workflow, source anchor, and regression risk.

Agent operating rules:

• Treat package.json as the Dojo version authority.
• Do not turn feature inventory into user-facing lessons without workflow context.
• Update this Dojo package when package behavior, docs, examples, or feature inventory changes.
• Verify downstream packages when package use and connection metadata shows inbound dependencies or references.
• Never mark publish status passed without successful cloud publish and catalog lookup.

Use this Dojo skill with package human docs, package-local feature inventory, agent-skillset.md, and the generated course.json in this folder. Keep this manifest version aligned with package.json.