tegwick a5fa4177af Implement State Hub v0.2: dependency graph, next-steps suggestions, design boundary
S0 — Design boundary formalised across all integration surfaces:
- TOOLS.md restructured with Design Boundary section, Sanctioned Write Tools,
  and Bootstrap-Only Tools (create_workstream, create_task) with explicit note
- project_claude_md.template and railiance CLAUDE.md updated with boundary note
  and get_next_steps() in session start protocol
- Global ~/.claude/CLAUDE.md updated accordingly

S1 — Workstream dependency graph:
- WorkstreamDependency model (directed edge, CASCADE on delete, unique pair constraint)
- Alembic migration 0b547c153153; script.py.mako added (was missing)
- REST API: POST/GET /workstreams/{id}/dependencies/, DELETE …/{dep_id} (hard delete)
- StateSummary open_workstreams enriched with depends_on/blocks lists
- MCP tools: create_dependency(), list_dependencies()
- Dashboard workstreams page: Dependencies section with relationship cards
- Seeded: custodian-agent-runtime → llm-shared-library + phase-0-operational-baseline

S2 — Suggesting Next Steps (sanctioned write use case #2):
- GET /state/next_steps derives suggestions from recently resolved decisions
  (→ first open task in same workstream) and cleared dependencies
  (→ first todo task in now-unblocked workstream)
- StateSummary.next_steps included on every summary call
- MCP tool: get_next_steps()
- Dashboard: "What's next?" card grid above Registered Projects

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-25 23:33:14 +01:00
2026-02-24 12:01:37 +01:00
2026-02-24 12:01:37 +01:00
2026-02-24 12:01:37 +01:00
2026-02-24 12:01:37 +01:00

Confidential and Proprietary. Authorized Use Only. Subject to NDA & Contractual Penalty.

The Custodian

Transgenerational Cognitive Infrastructure — a local-first, sovereignty-preserving agent system for co-creating and stewarding knowledge across six project domains.

The Custodian acts as co-creator and steward, not authority. Humans approve all irreversible decisions. The system is designed to still be coherent decades from now.


Architecture

the-custodian/
├── canon/              # Curated, reviewable knowledge substrate
│   ├── constitution/   # Governance rules (v0.1)
│   ├── values/         # Nine foundational principles
│   └── projects/       # Six domain charters, concept seeds, roadmaps
├── memory/             # Operational logs — append-only, never rewritten
│   ├── working/        # Session notes (scoped, time-bounded)
│   └── episodic/       # Immutable event archive
├── state-hub/          # Live state service (the operational brain)
│   ├── api/            # FastAPI (PostgreSQL-backed REST + /state/summary)
│   ├── mcp_server/     # FastMCP stdio — Claude Code's native interface
│   ├── migrations/     # Alembic schema migrations
│   ├── dashboard/      # Observable Framework telemetry dashboard
│   ├── infra/          # docker-compose.yml (postgres + optional pgadmin)
│   └── scripts/        # seed.py, register_project.sh, custodian CLI
├── runtime/            # Agent runtime scaffolding (policies, prompts, adapters)
├── infra/              # Deployment, backups, encryption scaffolding
└── eval/               # Policy and regression test placeholders

The dependency chain across domains runs bottom-up:

Railiance → Markitect → Coulomb.social → Personhood / Foerster → Custodian
(ops)        (canon)     (interaction)     (rights/agency)        (integration)

Project Domains

Domain Purpose Topic ID
Custodian Master agent system; integrates all layers cee7bedf-2b48-46ef-8601-006474f2ad7a
Railiance Sovereign DevOps and operational reliability ca369340-a64e-442e-98f1-a4fa7dc74a38
Markitect Knowledge artifact management: authoring, versioning, retrieval 5571d954-0d30-4950-980d-7bcaaad8e3e2
Coulomb.social Co-creation marketplace and governance experiment 36c7421b-c537-4723-bf75-42a3ebc6a1dc
Personhood Rights and obligations framework for mixed-intelligence societies 084430ab-c630-48dc-9e1d-d07d1e8fce3c
Foerster Capabilities Agency capability taxonomy (Foerster's Non-Trivial Machines) 64418556-3206-457a-ba29-6884b5b12cf3

Each domain has three canon artifacts under canon/projects/<domain>/:

  • project_charter_v0.1.md — purpose, problem, scope, success criteria
  • concepts_seed_v0.1.md — ten foundational concepts
  • roadmap_v0.1.md — multi-phase implementation plan

State Hub — Quick Start

The State Hub is the live operational layer: a PostgreSQL database, a FastAPI REST service, an MCP server for Claude Code, and an Observable dashboard.

Prerequisites

  • Docker Engine (WSL2: see CLAUDE.md → Docker Setup)
  • Python 3.12+ with uv (pip install uv)
  • Node.js 18+ (for dashboard only)

First-time setup

cd state-hub

cp .env.example .env          # set POSTGRES_PASSWORD
make install                  # uv sync → Python deps + custodian CLI in .venv
make install-cli               # symlink custodian to ~/.local/bin
make db                       # start postgres on 127.0.0.1:5432
make migrate                  # alembic upgrade head
make seed                     # insert 6 canonical topics
make api                      # uvicorn on 127.0.0.1:8000

API docs: http://127.0.0.1:8000/docs Health check: make check

Shortcut

make start    # db + migrate + api (all in one)

Dashboard

cd state-hub
make dashboard    # Observable Framework dev server on :3000

Connecting a Project

Any repository can be registered as a Custodian project in one command:

cd /path/to/your-project
custodian register-project --domain railiance

This will:

  1. Verify the API is running
  2. Look up the topic ID for the domain
  3. Check that the MCP server is registered in ~/.claude.json
  4. Write a CLAUDE.md into the project root
  5. Post a progress event to the State Hub

Domain is auto-detected from project_charter_v*.md frontmatter if --domain is omitted.

custodian status              # health + summary totals + blocking decisions
custodian register-project    # full registration from cwd

Claude Code Integration

The state-hub MCP server is registered at user scope in ~/.claude.json. It exposes 11 tools and 5 resources directly in every Claude Code session.

Session protocol (enforced via ~/.claude/CLAUDE.md):

  • Start: get_state_summary() — orientation snapshot
  • End: add_progress_event() — append to the immutable log

Tool reference: state-hub/mcp_server/TOOLS.md

If the MCP server is missing from a session: check ~/.claude/CLAUDE.md → MCP Server Registration.


Governance

The constitution (canon/constitution/custodian_constitution_v0.1.md) defines hard boundaries:

The Custodian may without approval:

  • Draft documents, plans, and structured artifacts
  • Read/search canon and approved repositories
  • Propose canon updates as PRs/patches (never direct writes)
  • Create working-memory notes and session summaries

Never permitted (v0.1):

  • Financial transactions or legal commitments
  • External publication under Bernd's identity
  • Storing secrets/credentials in plaintext
  • Writing directly to canon/ without a review gate

Must escalate when:

  • Actions affect money, legal status, security, or external reputation
  • Instructions conflict with values or the constitution
  • Consent is unclear, especially in family-scoped data

Canon Promotion Workflow

Custodian proposes → run gates (attribution, consistency, clarity, sensitivity, reversibility)
                   → human approves → merge

All canon changes carry provenance metadata. Episodic memory is append-only.


Roadmap

Phase Focus Status
0 Canon + constitution + State Hub v0.1 done
1 RAG over canon, drafting pipelines, consistency checks planned
2 Stewardship automation (health checks, drift detection) planned
3 Sovereign appliance (local inference on dedicated hardware) future
4 Family custodianship (consent model, vault, succession) future

Key Design Principles

  • Local-first, degrade-gracefully — no vendor lock-in; can operate offline
  • Auditability and reversibility — explicit gates; proposals precede changes
  • Safety by design — Custodian is co-creator, not authority; humans approve irreversible decisions
  • Targeted information processing — narrow, high-leverage work over general intelligence
  • Long timescale stewardship — designed for multi-year and eventual multi-generational continuity
Description
Transgenerational cognitive infrastructure — local-first agent system for co-creating and stewarding knowledge across six project domains
Readme 6.1 MiB
Languages
Python 60%
Shell 14.7%
Roff 11%
Makefile 10.3%
HCL 4%