terraphim / terraphim/terraphim-ai

Constitutional guardrails (CONSTITUTION.md) for agent supervisor

Open
#596 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

architecture enhancement multi-agent
Dominant language
Rust
Stars
62
Forks
5
Avg merge
2h 27m
Merged PRs (30d)
1

Description

Summary

Create an immutable set of architectural principles (CONSTITUTION.md) that terraphim agents cannot violate, even when given explicit instructions to do so. Enforced by terraphim_agent_supervisor as a pre-execution validation step.

Motivation

Inspired by Ouroboros BIBLE.md pattern. The agent system crates are incomplete partly because there is no specification of what agents MUST NOT do. A constitution constrains the design space, making it easier to complete the agent layer because boundaries are clear.

Proposed Principles

  1. Privacy-first: No data leaves the device unless explicitly configured by the user
  2. Deterministic-first: Prefer Aho-Corasick automata over LLM when deterministic matching suffices
  3. Type-safe: No unwrap() in library crates; all errors propagated via Result
  4. Compile-time checked: Prefer compile-time guarantees over runtime reflection
  5. Local-first: Offline operation is the default; network is optional
  6. Auditable: Every agent decision must be traceable to an input and a rule
  7. Reversible: Agent actions should be reversible where possible; destructive actions require confirmation

Implementation Plan

  1. Create CONSTITUTION.md at repo root with the principles above (editable by maintainers, versioned in git)
  2. Embed as a compile-time resource via rust-embed (already used in terraphim_agent and desktop)
  3. Add ConstitutionValidator to terraphim_agent_supervisor:
    • Pre-execution hook: check proposed agent action against constitution rules
    • Rules encoded as structured checks (not LLM interpretation)
    • Violation = action rejected with reason, logged as event
  4. Cryptographically sign the constitution using existing zipsign infrastructure from terraphim_update
  5. Add integration tests: attempt constitutional violations, verify rejection

Affected Crates

  • terraphim_agent_supervisor (primary -- add validation)
  • terraphim_types (add ConstitutionRule type)
  • terraphim_agent (embed constitution resource)

Estimated Effort

~2 hours

Part of

Epic #595

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the affected crates listed in the issue: terraphim_agent_supervisor, terraphim_types, and terraphim_agent, then inspect the existing rust-embed and zipsign usage. Define the constitution resource, structured validation and signing boundaries, and integration tests for rejected violations. Done means the documented rules are embedded, validated before execution, logged on rejection, and covered by tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
ai, backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.