Agent.md

Agent Deployment Information

1. Deployment Configuration

Target Space

• Profile: Leon4gr45
• Space: openweb
• Full Identifier: Leon4gr45/openweb
• Frontend Port: 7860 (mandatory for all Hugging Face Spaces)

Deployment Method

• Docker SDK — Chosen for flexibility to run both the Python app and the Pinchtab Go binary.

HF Token

• The environment variable HF_TOKEN is used for deployment and monitoring.

Required Files

• Dockerfile

• README.md with Hugging Face YAML frontmatter: ```yaml

  title: OpenResearcher sdk: docker app_port: 7860

• .hfignore
• Agent.md

---

2. API Exposure and Documentation

Mandatory Endpoints

• /health: Returns HTTP 200 when the app is ready.
• /api-docs: Documents all available API endpoints.

Functional Endpoints

• GET /health
  • Purpose: Health check for Hugging Face Space.
  • Response: {"status": "ok"}
• GET /api-docs
  • Purpose: API Documentation.
  • Response: HTML documentation.
• POST /predict (via Gradio)
  • Purpose: Main research agent interface.

---

3. Deployment Workflow

Standard Deployment Command

hf upload Leon4gr45/openweb --repo-type=space

Monitoring Logs

Build logs:

curl -N -H "Authorization: Bearer $HF_TOKEN" "https://huggingface.co/api/spaces/Leon4gr45/openweb/logs/build"

Run logs:

curl -N -H "Authorization: Bearer $HF_TOKEN" "https://huggingface.co/api/spaces/Leon4gr45/openweb/logs/run"