docs: add comprehensive architecture guide

[hoangsonww]

• Add ARCHITECTURE.md detailing 7-layer system design, data flows, deployment, and extension points
• Update README to link to architecture guide in Table of Contents and deployment section
• Remove badge section comments for cleaner badge display
• Minor formatting improvements for clarity
• Update release workflow to trigger on tags (v*) and generate release notes

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a detailed architecture guide for the Agentic Multi-Stage Bot, providing a clear understanding of the system's design and deployment. It also improves the README and release workflow for better maintainability and user experience.

Highlights

• Architecture Guide: Added a comprehensive ARCHITECTURE.md guide detailing the 7-layer system design, data flows, deployment, and extension points of the Agentic AI monorepo.
• README Update: Updated the README to include a link to the new architecture guide in the Table of Contents and deployment section, enhancing discoverability.
• Release Workflow: Modified the release workflow to trigger on tags (v*) and automatically generate release notes, streamlining the release process.
• Formatting Improvements: Implemented minor formatting improvements in the README for enhanced clarity and readability.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/release.yml

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds a comprehensive architecture guide in ARCHITECTURE.md, detailing the system's 7-layer design, data flows, and deployment. The README.md is also updated to link to this new guide and has had some formatting improvements. The new documentation is excellent and very thorough. I've included one minor suggestion to improve the accuracy of the entity-relationship diagram within the new architecture guide.

[gemini-code-assist]

The entity relationships in the Mermaid erDiagram could be more precise. The current notation for cardinalities doesn't fully align with the described SQL schema. For instance, MESSAGE ||--o| FEEDBACK implies a 'one-or-more-to-one' relationship, whereas the schema supports a 'one-to-many' relationship (one message can have multiple feedbacks).

To improve accuracy, I suggest updating the relationship markers to correctly represent the one-to-many (or one-to-zero-or-more) nature of the connections between entities.

Suggested change

	CHAT ||--o{ MESSAGE : contains
	CHAT ||--o{ FEEDBACK : receives
	MESSAGE ||--o| FEEDBACK : "rated by"
	KB_DOCUMENT ||--o{ KB_METADATA : has
	CHAT |o--o{ MESSAGE : contains
	CHAT |o--o{ FEEDBACK : receives
	MESSAGE |o--o{ FEEDBACK : "rated by"
	KB_DOCUMENT |o--o{ KB_METADATA : has