Rename Agments.md to AGENTS.md and standardize formatting

(cherry picked from commit 6e39c0c0ff)
This commit is contained in:
yangdx 2025-10-10 11:53:52 +08:00 committed by Raphaël MANSUY
parent c2c6ac3a45
commit 7de2cd98f6

View file

@ -1,6 +1,6 @@
# Project Guide for AI Agents # Project Guide for AI Agents
This Agments.md file provides operational guidance for AI assistants collaborating on the LightRAG codebase. Use it to understand the repository layout, preferred tooling, and expectations for adding or modifying functionality. This AGENTS.md file provides operational guidance for AI assistants collaborating on the LightRAG codebase. Use it to understand the repository layout, preferred tooling, and expectations for adding or modifying functionality.
## Core Purpose ## Core Purpose
@ -41,9 +41,8 @@ LightRAG is an advanced Retrieval-Augmented Generation (RAG) framework designed
## Frontend Development ## Frontend Development
* **Package Manager**: **ALWAYS USE BUN** - Never use npm or yarn unless Bun is unavailable - **Package Manager**: **ALWAYS USE BUN** - Never use npm or yarn unless Bun is unavailable
**Commands**: **Commands**:
- `bun install` - Install dependencies - `bun install` - Install dependencies
- `bun run dev` - Start development server - `bun run dev` - Start development server
@ -56,9 +55,8 @@ LightRAG is an advanced Retrieval-Augmented Generation (RAG) framework designed
- `bun run preview` - Preview production build - `bun run preview` - Preview production build
- **Pattern**: All frontend operations must use Bun commands
* **Pattern**: All frontend operations must use Bun commands - **Testing**: Use `bun test` for all frontend testing
* **Testing**: Use `bun test` for all frontend testing
## Coding Conventions ## Coding Conventions
@ -79,9 +77,9 @@ LightRAG is an advanced Retrieval-Augmented Generation (RAG) framework designed
- **Why**: Prevents different lock keys for same relationship pair processed in different orders - **Why**: Prevents different lock keys for same relationship pair processed in different orders
- **Apply to**: Any function that uses locks with multiple parameters - **Apply to**: Any function that uses locks with multiple parameters
* Priority Queue Implementation * Priority Queue Implementation
* **Pattern**: Use priority-based task queuing for LLM requests - **Pattern**: Use priority-based task queuing for LLM requests
* **Benefits**: Critical operations get higher priority - **Benefits**: Critical operations get higher priority
* **Implementation**: Lower priority values = higher priority - **Implementation**: Lower priority values = higher priority
## Testing and Quality Gates ## Testing and Quality Gates