flowstate-dojo-community-epicdm-flowstate-ai-gateway-core

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

Package identity:

• Package: @epicdm/flowstate-ai-gateway-core
• Repository: epic-flowstate-community
• Version authority: package.json (0.1.7)
• Dojo course: flowstate-dojo-community-epicdm-flowstate-ai-gateway-core

How to use the package:

• Purpose: Shared core for the FlowState AI Gateway (local container + Cloudflare worker). Provider adapters, cost tables, SSE usage tap, ledger store interface, budget policy.
• 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:

• PayloadAuditStatus
• PayloadAuditKind
• PayloadAuditItem
• PayloadAuditBundle
• PayloadCaptureOptions
• captureRequestPayload
• captureResponsePayload
• captureClonedResponsePayload
• mergePayloadAudits
• buildStaticResponsePayloadAudit
• ComputedCost
• computeCost
• normalizeAnthropicUsage
• normalizeOpenAIUsage
• PricePer1M
• PRICES
• PROVIDER_ALIASES
• findPrice
• MessagesHandlerConfig
• GatewayLogEvent
• handleProviderRequest
• handleMessages
• HDR_AGENT
• HDR_AGENT_ID
• HDR_ORG
• HDR_WORKSPACE
• HDR_SESSION
• HDR_REQUEST
• HDR_TRACE
• HDR_TASK

Composable feature skilllets:

• Adapter Wire Format: use feature labs for workflow, source anchor, and regression risk.
• Anthropic Direct Adapter: use feature labs for workflow, source anchor, and regression risk.
• Anthropic Sse Tap: use feature labs for workflow, source anchor, and regression risk.
• Build Anthropic Passthrough Url: use feature labs for workflow, source anchor, and regression risk.
• Build Non Streaming Open AIResult: use feature labs for workflow, source anchor, and regression risk.
• Build Non Streaming Result: use feature labs for workflow, source anchor, and regression risk.
• Build Open AIPassthrough Url: use feature labs for workflow, source anchor, and regression risk.
• Build Open AIPassthrough Url For Route: use feature labs for workflow, source anchor, and regression risk.
• Build Static Response Payload Audit: use feature labs for workflow, source anchor, and regression risk.
• Build Streaming Open AIResult: use feature labs for workflow, source anchor, and regression risk.
• Build Streaming Result: use feature labs for workflow, source anchor, and regression risk.
• Capture Cloned Response Payload: use feature labs for workflow, source anchor, and regression risk.
• Capture Request Payload: use feature labs for workflow, source anchor, and regression risk.
• Capture Response Payload: use feature labs for workflow, source anchor, and regression risk.
• Check Daily Budget: use feature labs for workflow, source anchor, and regression risk.
• Cloudflare Ai Gateway Adapter: use feature labs for workflow, source anchor, and regression risk.
• Cloudflare Ai Gateway Open AIAdapter: use feature labs for workflow, source anchor, and regression risk.
• Compute Cost: use feature labs for workflow, source anchor, and regression risk.
• Enforce Daily Budget: use feature labs for workflow, source anchor, and regression risk.
• Evaluate Budget Status: use feature labs for workflow, source anchor, and regression risk.
• Extract Usage From Body: use feature labs for workflow, source anchor, and regression risk.
• Extract Usage From Open AIBody: use feature labs for workflow, source anchor, and regression risk.
• Find Price: use feature labs for workflow, source anchor, and regression risk.
• Flow State Cloud Adapter: use feature labs for workflow, source anchor, and regression risk.
• Handle Messages: use feature labs for workflow, source anchor, and regression risk.
• Handle Provider Request: use feature labs for workflow, source anchor, and regression risk.
• HDR_AGENT: use feature labs for workflow, source anchor, and regression risk.
• HDR_AGENT_ID: use feature labs for workflow, source anchor, and regression risk.
• HDR_CONVERSATION: use feature labs for workflow, source anchor, and regression risk.
• HDR_IDENTITY_SIGNATURE: use feature labs for workflow, source anchor, and regression risk.
• HDR_IDENTITY_TIMESTAMP: use feature labs for workflow, source anchor, and regression risk.
• HDR_ORG: use feature labs for workflow, source anchor, and regression risk.
• HDR_REQUEST: use feature labs for workflow, source anchor, and regression risk.
• HDR_ROUTE_FROM: use feature labs for workflow, source anchor, and regression risk.
• HDR_ROUTE_TO: use feature labs for workflow, source anchor, and regression risk.
• HDR_SESSION: use feature labs for workflow, source anchor, and regression risk.
• HDR_TASK: use feature labs for workflow, source anchor, and regression risk.
• HDR_TRACE: use feature labs for workflow, source anchor, and regression risk.
• HDR_WORKSPACE: use feature labs for workflow, source anchor, and regression risk.
• In Memory Ledger Store: use feature labs for workflow, source anchor, and regression risk.
• 21 additional feature skilllets are listed in dojo-manifest.json and agent-skillset.md.

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.