mirror of https://github.com/furyhawk/ai_agent.git synced 2026-07-20 09:45:44 +00:00

Files

T

furyhawk 8351e73d39 feat: add Zustand stores for conversation, file preview, sidebar, theme, and knowledge base selection

- Implemented `conversation-store` for managing conversations and messages.
- Created `file-preview-store` to handle file preview state.
- Added `sidebar-store` for sidebar visibility management.
- Developed `theme-store` for theme persistence and management.
- Introduced `kb-selection-store` for managing active knowledge base selections with persistence.

chore: define API and chat types

- Added types for API responses, authentication, chat messages, conversations, and projects.
- Defined interfaces for various entities including users, sessions, and message ratings.

build: configure TypeScript and testing setup

- Set up `tsconfig.json` for TypeScript configuration.
- Created `vitest.config.ts` for testing configuration with Vitest.
- Added `vitest.setup.ts` for global test setup including mocks for Next.js router and media queries.
- Configured Vercel deployment settings in `vercel.json`.

2026-06-11 16:54:43 +08:00

1.8 KiB

Raw Permalink Blame History

AGENTS.md

This file provides guidance for AI coding agents (Codex, Copilot, Cursor, Zed, OpenCode).

Project Overview

ai_agent - FastAPI application generated with Full-Stack AI Agent Template.

Stack: FastAPI + Pydantic v2, PostgreSQL , JWT + API Key auth, Redis , pydantic_ai (openai), RAG (milvus), Next.js 15 (i18n)

Commands

# Run server
cd backend && uv run uvicorn app.main:app --reload

# Tests & lint
pytest
ruff check . --fix && ruff format .

# Migrations
uv run alembic upgrade head
uv run alembic revision --autogenerate -m "Description"

# RAG
uv run ai_agent rag-ingest /path/to/file.pdf --collection docs
uv run ai_agent rag-search "query" --collection docs

# Sync Sources
uv run ai_agent cmd rag-sources
uv run ai_agent cmd rag-source-add
uv run ai_agent cmd rag-source-sync

Project Structure

backend/app/
├── api/routes/v1/    # Endpoints
├── services/         # Business logic
├── repositories/     # Data access
├── schemas/          # Pydantic models
├── db/models/        # DB models
├── agents/           # AI agents
├── rag/              # RAG (embeddings, vector store, ingestion)
│   └── connectors/   # Sync source connectors
└── commands/         # CLI commands

Key Conventions

db.flush() in repositories, not commit()
Services raise NotFoundError, AlreadyExistsError
Separate Create, Update, Response schemas
Commands auto-discovered from app/commands/
Document ingestion via CLI and API upload
Sync sources: configurable connectors with scheduled sync

More Info

docs/architecture.md - Architecture details
docs/adding_features.md - How to add features
docs/testing.md - Testing guide
docs/patterns.md - Code patterns

1.8 KiB Raw Permalink Blame History