chore: add CLAUDE.md and AGENTS.md for AI-assisted development

[JAVGan]

Add CLAUDE.md with project guidance for Claude Code, covering development commands (tox environments, running single tests), code style rules (black, isort, flake8, mypy strict, 100% coverage), architecture overview (client, models, session, providers), and dependency management (pip-tools workflow).

AGENTS.md is a symlink to CLAUDE.md so other AI coding tools can also discover the guidance.

Refers to SPSTRAT-736

Summary by Sourcery

Add AI-assistant guidance documentation for working with the StArMap client repository and expose it via a generic entrypoint file for other tools.

Documentation:

• Introduce CLAUDE.md with project overview, development commands, code style, architecture, testing, and dependency management guidance for AI-assisted development.

Chores:

• Add AGENTS.md as a pointer file to CLAUDE.md so other AI coding tools can discover the same guidance.

[sourcery-ai]

Reviewer's Guide

Adds AI-assistant guidance documentation in CLAUDE.md describing development workflows, tooling, code style, architecture, and dependency management for the StArMap client, plus an AGENTS.md file that points other AI tools at the same guidance.

Flow diagram for AI tools discovering CLAUDE.md guidance

flowchart TD
    A["AI coding tool scans repository"] --> B{File discovered}
    B -->|CLAUDE.md| C["Read CLAUDE.md for guidance"]
    B -->|AGENTS.md| D["Follow pointer to CLAUDE.md"]
    D --> C
    C --> E["Apply development commands, code style, and architecture rules"]

Loading

File-Level Changes

Change	Details	Files
Introduce CLAUDE-specific contributor guide documenting development workflow, tooling, architecture, and standards for the project.	Add markdown documentation describing how to run tests, linting, type checking, security scans, docs builds, and dependency pinning via tox environments. Document code style conventions including black, isort, flake8 with specific docstring rules, strict mypy usage, and enforced 100% coverage. Provide a high-level architecture overview of core client, models, session abstraction, providers, and testing layout. Describe dependency management using pip-tools and the relationship between unpinned and pinned requirement files.	CLAUDE.md
Expose the CLAUDE guidance to other AI coding tools via a simple indirection file.	Create an AGENTS.md file whose contents reference CLAUDE.md so alternate AI tools can reuse the same project guidance.	AGENTS.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[JAVGan]

@lslebodn @ashwgit PTAL

[sourcery-ai]

Hey - I've left some high level feedback:

• AGENTS.md is currently a plain file containing the text CLAUDE.md; if the intent is a real symlink for tooling, consider committing it as an actual symlink or adding a brief header that explains it is an alias to CLAUDE.md so tools and humans don’t misinterpret it.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- AGENTS.md is currently a plain file containing the text `CLAUDE.md`; if the intent is a real symlink for tooling, consider committing it as an actual symlink or adding a brief header that explains it is an alias to CLAUDE.md so tools and humans don’t misinterpret it.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}