#114 doc: Fixup markdown documentation

[arekay-nv]

What does this PR do?

Fixes documentation.
Closes #114

Type of change

• Bug fix
• New feature
• Documentation update
• Refactor/cleanup

Related issues

Testing

• Tests added/updated
• All tests pass locally
• Manual testing completed

Checklist

• Code follows project style
• Pre-commit hooks pass
• Documentation updated (if needed)

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[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 focuses on enhancing the clarity and accuracy of the project's documentation. It addresses outdated information regarding command-line interface parameters, streamlines the development environment setup, and refines the description of the project's internal structure and dependency management practices. The changes aim to provide a more consistent and up-to-date guide for both users and developers.

Highlights

• Documentation Updates for CLI Arguments: Updated various documentation files to reflect changes in CLI arguments, specifically replacing --output with --timeout for YAML mode overrides and standardizing --report-path to --report-dir for benchmark reports.
• Development Workflow Streamlining: Revised the development setup instructions to use pip install -e ".[dev,test]" for dependency management and updated code formatting and linting tools from Black/isort/flake8 to Ruff.
• Project Structure Clarification: Adjusted the documented project directory structure by removing references to the runtime/ and requirements/ directories, and added new utility files to the AGENTS.md overview.
• Dependency Management Modernization: Updated documentation to guide users towards managing dependencies via pyproject.toml instead of separate requirements/ files.

🧠 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.

Changelog

• AGENTS.md
  • Updated the description of YAML mode CLI overrides to use --timeout instead of --output.
  • Added a description for the eval CLI mode.
  • Updated the directory structure to include eval.py and utils.py under src/inference_endpoint/commands/.
  • Updated the directory structure to include utils.py under src/inference_endpoint/load_generator/.
  • Updated the directory structure to include user_config.py under src/inference_endpoint/rulesets/.
  • Updated the directory structure to include benchmark_httpclient.py under src/inference_endpoint/utils/.
• docs/CLI_QUICK_REFERENCE.md
  • Replaced --output and --report-path with --report-dir in benchmark command examples.
  • Updated the YAML mode CLI override description and example to use --timeout instead of --output.
  • Updated best practices to recommend --report-dir instead of --report-path.
• docs/DEVELOPMENT.md
  • Updated the dependency installation command to pip install -e ".[dev,test]".
  • Removed the runtime/ directory from the documented project structure.
  • Removed the requirements/ directory from the documented project structure.
  • Modified pytest.mark.asyncio decorator to include mode="strict" in the example.
  • Updated code formatting commands from black and isort to ruff format.
  • Updated linting commands from flake8 to ruff check.
  • Revised instructions for adding and updating dependencies to refer to pyproject.toml.
• docs/LOCAL_TESTING.md
  • Replaced --output and --report-path with --report-dir in various benchmark examples.
  • Simplified the 'View Results' section, replacing detailed jq commands with a general description of --report-dir output.
  • Adjusted step numbering in the 'Local Testing' guide.

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.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

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 updates several documentation files to align with recent changes in the project's tooling and API. Key changes include updating dependency management instructions to use pyproject.toml, replacing black/isort/flake8 with ruff, and reflecting API changes like renaming --report-path to --report-dir. The documentation changes are mostly accurate and consistent. However, I've identified a couple of areas in the examples within docs/LOCAL_TESTING.md where removing result-checking commands has made the examples less complete. My suggestions aim to restore this helpful information for users.

[Copilot]

Pull request overview

Updates repository documentation to reflect recent CLI and developer workflow changes (notably shifting benchmark reporting to --report-dir, moving dependency management to pyproject.toml extras, and standardizing on Ruff).

Changes:

• Replace --report-path (and --output in examples) with --report-dir across local testing and CLI quick reference docs.
• Update development setup instructions to use pip install -e ".[dev,test]" and Ruff for formatting/linting.
• Refresh AGENTS.md CLI-mode notes and the source tree map to match current module layout.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File	Description
docs/LOCAL_TESTING.md	Updates benchmark examples to use --report-dir and revises “View Results” guidance.
docs/DEVELOPMENT.md	Aligns dev setup, formatting, linting, pytest-asyncio guidance, and dependency instructions with current tooling.
docs/CLI_QUICK_REFERENCE.md	Updates benchmark examples and YAML-mode notes to match current CLI flags/constraints.
AGENTS.md	Updates CLI mode constraints and source tree listing to reflect current code organization.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

[nvzhihanj]

Review Council — Multi-AI Code Review Council

Reviewed by: Claude
(Codex was unavailable — shell commands blocked in exec mode)

Found 0 issues across 6 files.

Verification Summary

The Claude reviewer verified each documentation change against the actual codebase:

• --report-path → --report-dir: confirmed --report-dir exists, --report-path does not
• --output → --timeout (for from-config): confirmed _add_auxiliary_args only adds --timeout
• black/isort/flake8 → ruff: confirmed tooling matches current setup
• requirements/ → pyproject.toml: confirmed dependency management approach
• New files in AGENTS.md tree (eval.py, utils.py, user_config.py, benchmark_httpclient.py): all verified to exist
• LiveCodeBench README link fix (dataset_manager/predefined/livecodebench/ → evaluation/livecodebench/): confirmed new path exists
• Removed runtime/ directory reference: confirmed it no longer exists
• @pytest.mark.asyncio → @pytest.mark.asyncio(mode="strict"): matches project convention

All changes are factually accurate and align with the current state of the codebase.

🤖 Generated with Claude Code