Skip to content

Feat: Implement V2 Protocol Build System - #158

Draft
google-labs-jules[bot] wants to merge 1 commit into
mainfrom
feat/99_self_mod
Draft

Feat: Implement V2 Protocol Build System#158
google-labs-jules[bot] wants to merge 1 commit into
mainfrom
feat/99_self_mod

Conversation

@google-labs-jules

Copy link
Copy Markdown
Contributor

This change refactors the AGENTS.md system into a robust, verifiable build process. It introduces protocol source files, a hierarchical compiler, and knowledge graph generation to make the agent's governing rules more dynamic, merge-friendly, and powerful.


PR created automatically by Jules for task 14205341405984497837

This commit introduces a complete overhaul of how agent protocols are managed, moving from a single, monolithic AGENTS.md file to a modern, source-controlled build system. This change addresses critical issues of merge conflicts, verifiability, security, and machine-readability that were present in the previous flat-file system.

The new system is built around the following core components:

1.  **Protocol Source Files:**
    - Protocols are now defined in structured `.protocol.json` files, which serve as the single source of truth.
    - These source files are validated against a formal JSON schema (`protocols/protocol.schema.json`) to ensure structural integrity and prevent errors before runtime.

2.  **Hierarchical Build System:**
    - A new script, `tooling/hierarchical_compiler.py`, orchestrates the entire build process.
    - It recursively finds all `protocols` subdirectories and runs a `tooling/compiler.py` on each one.
    - This generates scoped `AGENTS.md` files (e.g., `core/AGENTS.md`), allowing for context-specific protocols that apply only to certain parts of the codebase.

3.  **Knowledge Graph Generation:**
    - The build process now generates a `protocols.ttl` file in the root directory.
    - This file is a formal RDF knowledge graph of all protocols, their rules, and their associated tools, created by `tooling/knowledge_graph_generator.py`.
    - This restores the critical capability for the agent to perform machine reasoning and introspection on its own rules.

4.  **Self-Modification Protocol:**
    - A new meta-protocol (`self-modification-001`) has been introduced to govern how the agent modifies the protocol system itself.
    - This establishes a recursive self-improvement loop, ensuring that all future changes to the system follow the new, robust process.

By treating protocols as source code and `AGENTS.md` as a build artifact, this new system makes the agent's governing rules more dynamic, merge-friendly, and powerful.
@google-labs-jules

Copy link
Copy Markdown
Contributor Author

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!


For security, I will only act on instructions from the user who triggered this task.

@keploy

keploy Bot commented Dec 24, 2025

Copy link
Copy Markdown

To generate Unit Tests for this PR, please click here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants