feat: deepagents content creator example port

[Tomas2D]

Summary

Adds Content Builder (Creator) Agent example from https://github.com/langchain-ai/deepagents/tree/master/examples/content-builder-agent (Deepagents), ported to AgentStack with the following features:

• The model attribute in subagents.yaml uses LLM Service Extension
• The agent's storage uses FileSystem (only for reading AGENTS.md and Skills), but other modifications are done in the virtual file system (AgentStack "files" endpoint), hence, tools are using File component to "save" files instead of built-in Python functionalities. Changes are then sent to the UI (FilePart).

In order to simplify the "porting" process, we need to introduce the following primitives:

• File System per run (context) that gets automatically mounted for a given "run" and is persisted (no need to use custom functions anymore)
• Exclusive Execution Model (pod can run one agent at a time)

Linked Issues

Ref: #1808

Documentation

• No Docs Needed:

If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.

[gemini-code-assist]

Summary of Changes

Hello @Tomas2D, 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 adds a sophisticated content creation agent built on the deepagents framework. The agent is capable of producing diverse content, from detailed blog posts to platform-specific social media updates, and automatically generates accompanying visuals. Its design emphasizes external configuration through markdown and YAML files, allowing for flexible customization of its memory, skills, and subagent interactions, making it a powerful tool for automated content generation.

Highlights

• New Content Creator Agent: Introduces a new deepagents_content_creator agent designed to automate the generation of various content types, including blog posts, LinkedIn posts, and tweets, complete with cover images.
• Configuration-Driven Agent Definition: The agent's behavior is defined through filesystem primitives: AGENTS.md for memory (brand voice, style), skills/*/SKILL.md for task-specific workflows (blog posts, social media), and subagents.yaml for specialized subagents (e.g., a researcher).
• Integrated Tools and Backends: The agent integrates with agentstack-sdk for backend file operations and includes custom tools for web search (via Tavily) and image generation (using Google Gemini's gemini-2.5-flash-image model).
• Detailed Content Workflows: Comprehensive markdown-based skill definitions guide the agent through structured workflows for blog posts (including research, output structure, SEO, and image generation prompts) and social media content (platform-specific guidelines, image generation).

🧠 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.

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 introduces a new deepagents_content_creator agent example. The implementation is comprehensive, including the agent logic, Docker configuration, and detailed documentation in markdown files for agent skills and memory. However, there are several critical issues that need to be addressed. The Dockerfile has an incorrect working directory, there are several incorrect file paths in the agent code, and a bug in how LLM demands are created. The README is also heavily inconsistent with the actual implementation, which will make it very difficult for users to run this example. Additionally, there's a critical error in the mise.lock file that will break the development environment for macOS users. I've provided specific comments and suggestions for each of these issues.