Back to corpus
architecturetechnical paper candidatescore 46

RAG++ Architecture Diagram

```mermaid flowchart TB subgraph Sources [Data Sources] Claude[Claude Desktop<br/>Response Hooks] Cursor[Cursor/Codex<br/>IDE Integration] Echelon[Echelon Engine<br/>Trajectory Segments] Studio[CC Studio<br/>Session Logs] AgentSDK[Agent SDK<br/>Programmatic Access] end

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

**Version**: 2.1.0 **Last Updated**: 2026-01-03 **Parent**: [08-RAG_PLUS_PLUS.md](../08-RAG_PLUS_PLUS.md) Inverse Ring Contextual Propagation computes attention weights based on trajectory distance: | Factor | Default Weight | Description | |--------|----------------|-------------| | recency | 0.3 | Time since creation | | depth | 0.2 | Conversation depth | | impact | 0.3 | Measured influence | | role | 0.2 | User > Assistant > System | | Endpoint | Method | Purpose | |----------|--------|---------| | `/api/rag/health` | GET | Health check | | `/api/rag/ingest` | POST | Ingest turn | | `/api/rag/search` | GET | Semantic search | | `/api/rag/context/{project_id}` | GET | Project context | | `/api/rag/signature` | GET | Style signature | | `/api/rag/train` | POST | Trigger training | | Tool | Purpose | |------|---------| | `rag_search` | Search memory fabric | | `rag_context` | Get project context | | `rag_style_signature` | Get style signature |

Promotion decision

What has to happen next

Promote into a technical note or architecture paper with implementation anchors.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.