approval-engine/AGENTS.md

approval-engine — Agent Instructions

Repo Identity

Purpose: PIP for the approval object: durable, authenticated, consumable, atomically supersedable.

Domain: infotech Repo slug: approval-engine Topic ID: cee7bedf-2b48-46ef-8601-006474f2ad7a Workplan prefix: APPROVAL-WP-

---

State Hub Integration

The Custodian State Hub tracks work across all domains. Codex uses HTTP REST and the statehub CLI by default. MCP is opt-in because the current Codex MCP bridge adds severe call latency; the full administrative MCP surface remains available to clients that need it.

Context	URL
Local workstation	http://127.0.0.1:8000
Remote via tunnel	http://127.0.0.1:18000
Optional local edge relay	http://127.0.0.1:18080

When an operator has enabled the edge relay, set API_BASE to the relay URL. Queueable writes return an explicit queued receipt if the central hub is unreachable. Treat that as pending local evidence, then ask the operator to run statehub outbox status/replay after connectivity returns.

Codex workspace-write sandboxes need network access enabled to reach the host's loopback listener. Bootstrap this once with make -C ~/state-hub configure-codex and restart Codex. The canonical REST health endpoint is /state/health, not /health. If a sandboxed loopback probe fails, retry it with escalated execution before declaring State Hub unavailable; a managed Codex permission profile may still enforce isolated networking. Experimental MCP can be enabled explicitly with make -C ~/state-hub configure-codex WITH_MCP=1.

Orient at session start

# Offline brief — works without hub connection
cat .custodian-brief.md

# Active workplans for this domain
curl -s "http://127.0.0.1:8000/workplans/?topic_id=cee7bedf-2b48-46ef-8601-006474f2ad7a&status=active" \
  | python3 -m json.tool

# Check inbox
curl -s "http://127.0.0.1:8000/messages/?to_agent=approval-engine&unread_only=true" \
  | python3 -m json.tool

Mark a message read:

curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
  -H "Content-Type: application/json" -d '{}'

Log progress (required at session close)

curl -s -X POST http://127.0.0.1:8000/progress/ \
  -H "Content-Type: application/json" \
  -d '{
    "summary": "what was done",
    "event_type": "note",
    "author": "codex",
    "workplan_id": "<uuid>",
    "task_id": "<uuid>"
  }'

Omit workplan_id / task_id when not applicable.

Update task status

curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
  -H "Content-Type: application/json" \
  -d '{"status": "progress"}'
# values: wait | todo | progress | done | cancel

Flag a task for human review

curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
  -H "Content-Type: application/json" \
  -d '{"needs_human": true, "intervention_note": "reason"}'

---

Session Protocol

Start:

1. cat .custodian-brief.md — domain goal and open workplans (offline-safe)
2. Check inbox: GET /messages/?to_agent=approval-engine&unread_only=true; mark read
3. Scan workplans: ls workplans/ — note status: ready, active, or blocked files and open tasks
4. Check human-needed tasks: GET /tasks/?needs_human=true

During work:

• Update task statuses in workplan files as tasks progress
• Record significant decisions via POST /decisions/

Close:

1. Update workplan file task statuses to reflect progress
2. If finishing a workplan: hand off residuals as live work records first (intake with origin: residual + origin_ref: <WP-id>, or a next workplan / decision / engagement). Do not park leftovers only in prose or SCOPE.md. Canon: the-custodian/canon/standards/work-record-types_v0.1.md § Residuals.
3. Log: POST /progress/ with a summary of what changed (name handoff ids)
4. After workplan file changes, run:

   statehub fix-consistency
   

   Coding agents should run this directly; ask the operator only if the CLI or State Hub API is unavailable. This syncs task status from files into the hub DB. If C-06/C-11 reports that this host is not the identifier registrar, do not retry, export STATEHUB_REGISTRAR, or register records by hand. Commit and push the file-backed work first, then run the repo-manager fallback once:

   uv run --project ~/repo-manager rmgr registrar-reconcile \
     --path . --confirm-primary --push
   

   If unavailable, send one deduplicated registrar request to repo-manager naming the repo and canonical ids; UUID absence does not block local work.

---

Credential and access routing

Audience: Codex, Claude Code, Grok, and custodian agents that call llm-connect for inference. Run this check before requesting secrets, API keys, SSH access, login tokens, or database passwords — in any repo, not only ops-warden.

The companion (net-kingdom/SECURITY-COMPANION.md) says what the rules are; ops-warden stewards the paths through them. Do not message ops-warden on State Hub expecting a secret value; the reply is a pointer, not a key.

Lookup (do this first)

warden route find "<describe your need>" --json
warden route show <catalog-id> --json

Requires the warden CLI from ~/ops-warden.

Agent runtime	How to orient
Codex / Grok (shell, HTTP State Hub)	warden route; inbox to_agent=approval-engine is for coordination, not secret vending
Claude Code (MCP when available)	domain summary for workplans; still use warden route for credential ownership
llm-connect	Never put secret retrieval in prompts

Quick routing table

I need…	Owner	ops-warden executes?
SSH cert (adm/agt/atm)	ops-warden	Yes — warden sign
API key, DB password, provider token	OpenBao	No — route only
Login / OIDC / MFA	key-cape	No — route only
Authorization decision	access-engine (flex-auth)	No — route only
Approval current-state	this engine (not yet implemented)	No
SSH tunnel	ops-bridge	No — route only

Anti-patterns

• Asking State Hub or ops-warden to vend a secret
• Pasting secrets into Git, State Hub, workplans, logs, or chat
• Treating a callable tool as permission (companion §7)

Canon: ~/ops-warden/wiki/CredentialRouting.md

This repository's layer

Engine, role PIP. Statute v0.7, companion v0.2. Declaration: INTENT.md frontmatter and layer.yaml.

• Answer "is this approval valid for this exact binding, and has it been used?" Never "may this actor do X".
• Consumption follows GH-DEC-2026-003 and gate-house/docs/contracts/approval-consumption.md: the PEP consumes by CAS before the protected side effect; same-digest retries are idempotent, different digests conflict, and there is no unconsume.
• The outbox is local. Do not emit synchronously to audit-core inside a mutation transaction.
• Approval evidence is load-bearing. Atomicity covers crash, not compromise.
• An approval is not a Railiance workload.
• Remote hub: this host reaches State Hub on http://127.0.0.1:8000 (primary on railiance01). Do not use 127.0.0.1:18000 — that reverse tunnel is being retired (CUST-WP-0067).

---

Workplan Convention (ADR-001)

Work items originate as files in this repo — not in the hub. The hub is a read/cache/index layer that rebuilds from files.

File location: workplans/APPROVAL-WP-NNNN-<slug>.md

Archived location: finished workplans may move to workplans/archived/YYMMDD-APPROVAL-WP-NNNN-<slug>.md. The YYMMDD prefix is the completion/archive date; the frontmatter id does not change.

Ad Hoc Tasks: small opportunistic fixes discovered during a session use workplans/ADHOC-YYYY-MM-DD.md, workplan id APPROVAL-WP-ADHOC-YYYY-MM-DD, and task ids APPROVAL-WP-ADHOC-YYYY-MM-DD-T01, etc. APPROVAL-WP includes its final -WP token. Unqualified historic ADHOC-* ids are grandfathered and must not be copied into new records. Use this only for low-risk work completed directly; create a normal workplan for anything needing analysis, design, approval, dependencies, or multiple phases.

Frontmatter:

---
id: APPROVAL-WP-NNNN
type: workplan
title: "..."
domain: infotech
repo: approval-engine
status: proposed | ready | active | blocked | backlog | finished | archived
owner: codex
topic_slug: ...
created: "YYYY-MM-DD"
updated: "YYYY-MM-DD"
state_hub_workstream_id: "<uuid>"   # fix-consistency — do not edit (legacy field name; workplan UUID)
---

Use proposed for a new draft, ready after review against current repo state, and finished after implementation. stalled and needs_review are derived health labels, not frontmatter statuses.

Terminology: workplan is the fleet term; workstream appears only in legacy API/MCP/frontmatter bridges until STATE-WP-0069 retires them — see the-custodian/canon/standards/workplan-terminology-fleet_v0.1.md.

Task block format (one per ## section):

## Task Title

` ` `task
id: APPROVAL-WP-NNNN-T01
status: wait | todo | progress | done | cancel
priority: high | medium | low
state_hub_task_id: "<uuid>"         # written by fix-consistency — do not edit
` ` `

Task description text.

Status progression: todo → progress → done; use wait for waiting/blocked work and cancel for stopped work.

Residuals when finishing: actionable leftovers become live work records before status: finished — usually an intake (origin: residual, origin_ref: APPROVAL-WP-NNNN) or a spawned workplan. Residual is a role, not a kind. Fleet list lives on State Hub, not in SCOPE.md.

To create a new workplan:

1. Write the file following the format above
2. Run statehub fix-consistency locally.
3. On a non-registrar C-06/C-11 skip, use the repo-manager fallback documented above exactly once; never set registrar authority directly.