Fix Docker deployment and configuration documentation inconsistencies

[Copilot]

The Docker deployment documentation and configuration files contained multiple inconsistencies that caused validation errors during container startup. This fix addresses both the original HOST_URL vs AGENT_HOST_URL mismatch and additional configuration documentation issues.

Issues Fixed:

1. Environment variable name mismatch: Docker command showed HOST_URL but application expects AGENT_HOST_URL
2. Inconsistent .env.example: Still used deprecated HOST_URL variable name
3. Misleading documentation: DATA_FOLDER_PATH was listed as "optional" when it's actually required when S3 is disabled

Before (broken configuration):

# Docker command used wrong variable name
docker run -e HOST_URL=http://localhost:4322 ...

# .env.example showed incorrect variable
HOST_URL=http://localhost:4322

# Documentation incorrectly listed DATA_FOLDER_PATH as optional
**Optional Environment Variables:**
- `DATA_FOLDER_PATH`: Local storage path (default: `data`)

This caused validation errors:

ValidationError: 2 validation errors for AppConfig
agent_host_url
  Value error, agent_host_url environment variable is required.
data_folder_path
  Value error, Data folder path must be set when S3 is not enabled.

After (working configuration):

# Correct variable names throughout
docker run -e AGENT_HOST_URL=http://localhost:4322 ...
AGENT_HOST_URL=http://localhost:4322

# Clear storage configuration requirements
**Storage Configuration (choose one):**
When S3 is disabled (default), local storage is required:
- `DATA_FOLDER_PATH`: Local storage path for allocation data (required when `S3_ENABLED=false`)

Changes Made:

• Updated Docker command to use AGENT_HOST_URL instead of HOST_URL
• Fixed .env.example to use correct environment variable names
• Reorganized documentation to clearly explain storage configuration requirements
• Clarified that DATA_FOLDER_PATH is required when S3 is disabled (default behavior)

The corrected documentation now matches the actual validation logic in allocator_bot/models.py and is consistent across all configuration files including Kubernetes manifests.

Fixes #4.

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Copilot]

@piiq 👋 This repository doesn't have Copilot instructions. With Copilot instructions, I can understand the repository better, work faster and produce higher quality PRs.

I can generate a .github/copilot-instructions.md file for you automatically. Click here to open a pre-filled issue and assign it to me. I'll write the instructions, and then tag you for review.

[piiq]

@copilot check that the logic and the documentation around data_folder_path is correct. The

data_folder_path
  Value error, Data folder path must be set when S3 is not enabled.

error doesn't seem related to the host url.

[Copilot]

@copilot check that the logic and the documentation around data_folder_path is correct. The

data_folder_path...

You're absolutely correct! The data_folder_path error was unrelated to the host URL fix. I found and corrected several inconsistencies:

Issues found:

1. .env.example still had HOST_URL= instead of AGENT_HOST_URL=
2. README.md incorrectly listed DATA_FOLDER_PATH as "optional" when it's actually required when S3 is disabled
3. Documentation didn't clearly explain the storage configuration requirements

Fixed in commit 2526bd8:

• Updated .env.example to use correct AGENT_HOST_URL variable name
• Reorganized README.md environment variables section to clarify that DATA_FOLDER_PATH is required when S3_ENABLED=false (the default)
• Added clear storage configuration documentation explaining the either/or relationship between local and S3 storage

The validation logic in models.py was correct - it properly enforces that data_folder_path must be set when S3 is not enabled. The issue was that the documentation didn't match this validation requirement.