Atmosphere's unified AI abstraction layer sits between @AiEndpoint handlers and the four
supported AI frameworks (Spring AI, LangChain4j, Google ADK, Embabel). It provides:
@AiTool annotation → framework-agnostic ToolDefinition → native bridgesAiCapability enum + ModelRouter for smart routing/failoverConversationPersistence SPI backed by Redis or SQLite
Atmosphere currently integrates with 4 external AI frameworks plus a built-in OpenAI-compatible client:
| Framework | Module | Adapter | Request Type |
|---|---|---|---|
| Built-in OpenAI | modules/ai |
BuiltInAiSupport |
AiRequest |
| Spring AI | modules/spring-ai |
SpringAiStreamingAdapter |
ChatRequest |
Used during generate_skill BFS/DFS exploration for component classification.
SamplingBridge.swift / SamplingClassifiersampling/createMessage to the MCP client, which forwards it to whatever LLM the client is using (e.g. Claude via Claude Code)componentDetection in settings.json controls the mode:
Testing component detection on the Santé (Health) app reveals three problems:
row_has_chevron: true constraint causes hard failure.SAM (Segment Anything Model) was considered for bounding-box detection but rejected — too heavy (50-500MB). The existing absorption mechanism (absorbs_below_within_pt: 80) already handles bounding-box suppression correctly; the calibration tool just doesn't show it.
The key insight: Atmosphere's primitives (Broadcaster, BroadcasterCache, Interceptors, Rooms, Presence, Clustering) are proven patterns from 18 years of real-time work. No AI framework has equivalents because they all think model-out, not transport-out.
This document is optimized for LLM consumption. Use it to answer questions about Pierre's architecture, code patterns, and implementation details.
Pierre is a production Rust fitness API platform implementing:
Reference documentation for ChatGPT. Part 3: Tools, Sports Science, Nutrition.
Comprehensive reference for all 47 Model Context Protocol (MCP) tools provided by Pierre Fitness Platform. These tools enable AI assistants to access fitness data, analyze performance, manage configurations, and provide personalized recommendations.