Regenerate agent instructions from state-hub templates (CUST-WP-0055 T01)
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 3s

Sync AGENTS.md, CLAUDE.md, and .claude/rules from updated project_rules
templates: workplan-first session protocol, legacy terminology footnote,
and GET /workplans/ examples.
This commit is contained in:
tegwick 2026-07-08 14:50:19 +02:00
parent 8ea196298b
commit f8d0ef3c0f
8 changed files with 249 additions and 88 deletions

View file

@ -19,8 +19,8 @@ Requires the `warden` CLI from `~/ops-warden` (`uv tool install .` or `uv run wa
| Agent runtime | How to orient |
| --- | --- |
| **Codex / Grok** (shell, HTTP State Hub) | `warden route` commands above; inbox `to_agent=repo-seed` is for coordination, not secret vending |
| **Claude Code** (MCP when available) | `get_domain_summary("custodian")` for workstreams; **still** use `warden route` for credential ownership |
| **Codex / Grok** (shell, HTTP State Hub) | `warden route` commands above; inbox `to_agent=core-hub` is for coordination, not secret vending |
| **Claude Code** (MCP when available) | `get_domain_summary("custodian")` for workplans; **still** use `warden route` for credential ownership |
| **llm-connect** (inference service) | Never put secret retrieval in prompts; route custody to OpenBao/operator paths surfaced by `warden route` |
### Quick routing table

View file

@ -1,26 +1,42 @@
## First Session Protocol
Triggered when State Hub shows no workstreams for `core-hub`.
Triggered when `get_domain_summary("infotech")` shows **no workplans**.
The project is registered but work has not yet been structured.
**Step 1 - Read, do not write yet**
- `INTENT.md`
- `SCOPE.md`
- `docs/research/2026-06-27-core-hub-lineage-and-platform-reset.md`
- `docs/specs/README.md`
- Existing files under `workplans/`
**Step 1 — Read, don't write**
- `~/the-custodian/canon/projects/infotech/project_charter_v0.1.md` — purpose, scope
- `~/the-custodian/canon/projects/infotech/roadmap_v0.1.md` — planned phases
- Scan repo root: README, directory structure, existing code or docs
**Step 2 - Survey in-progress work**
Look for untracked files, open workplans, and half-finished specs. Note done vs. started but incomplete.
**Step 2 — Survey in-progress work**
Look for TODOs, open branches, half-finished files. Note done vs. started but incomplete.
**Step 3 - Structure work in files first**
Create or update `workplans/CORE-WP-NNNN-<slug>.md` before relying on State Hub records.
**Step 4 - Sync the read model**
After workplan changes, run from `~/state-hub`:
**Step 3 — Propose workplans to Bernd**
Propose 13 workplans — each a coherent strand, weeks to months, anchored to a
roadmap phase. **Wait for approval before creating.**
**Step 4 — Write the workplan file; fix-consistency registers it (ADR-001)**
```
workplans/CORE-WP-NNNN-<slug>.md ← write this, commit it
```
Then register by running the consistency check — do **not** call
`create_workplan`/`create_task` yourself; manual registration duplicates what
C-06 creates from the file:
```bash
make fix-consistency REPO=core-hub
statehub fix-consistency --repo core-hub
```
C-06 creates the hub workplan + tasks and writes `state_hub_workstream_id`
(legacy frontmatter name — holds the workplan UUID) and `state_hub_task_id`
back into the file.
**Step 5 — Record the setup**
```
add_progress_event(
summary="First session: structured infotech into N workplans, M tasks",
event_type="milestone",
topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a",
detail={"workplans": [...], "tasks_created": M}
)
```
**Step 5 - Record progress**
Post a non-secret progress note to State Hub summarizing the setup or implementation work.
<!-- Delete or archive this file once past first session -->

View file

@ -1,6 +1,6 @@
## Repo boundary
This repo owns **Repo Seed** only. It does not own:
This repo owns **core-hub** only. It does not own:
<!-- TODO: List what belongs in adjacent repos, e.g.:
- SSH key management → railiance-infra/

View file

@ -1,6 +1,5 @@
**Purpose:** 3rd-generation production interaction framework for Coulomb / Helixforge.
**Purpose:** Core Hub is the 3rd-generation production interaction and coordination framework for Coulomb / Helixforge, intended to supersede the 1st-generation state-hub and 2nd-generation inter-hub infrastructure.
**Domain:** infotech
**Repo slug:** core-hub
**Topic ID:** cee7bedf-2b48-46ef-8601-006474f2ad7a
**Workplan prefix:** CORE-WP-

View file

@ -1,48 +1,92 @@
## Session Protocol
Dev Hub (State Hub API): http://127.0.0.1:8000
MCP server name in `~/.claude.json`: `dev-hub`
**Step 1 - Orient**
**Step 1 Orient**
Read the offline-safe brief first — it works without a live hub connection:
```bash
cat .custodian-brief.md
cat INTENT.md
cat SCOPE.md
ls workplans/
```
Use REST when MCP tools are unavailable:
Then call the MCP tool for richer cross-domain context when MCP tools are exposed:
```
get_domain_summary("infotech")
```
If MCP tools are unavailable in the current agent session, use the REST API:
```bash
curl -s "http://127.0.0.1:8000/workstreams/?topic_id=cee7bedf-2b48-46ef-8601-006474f2ad7a&status=active" | python3 -m json.tool
curl -s "http://127.0.0.1:8000/state/summary" | python3 -m json.tool
```
If the hub is offline: `cd ~/state-hub && make api`
**Step 2 - Check inbox**
**Step 2 — Check inbox**
With MCP tools:
```
get_messages(to_agent="core-hub", unread_only=True)
```
Mark read with `mark_message_read(message_id)`. Reply or act on coordination
requests before proceeding.
Without MCP tools:
```bash
curl -s "http://127.0.0.1:8000/messages/?to_agent=core-hub&unread_only=true" | python3 -m json.tool
curl -s "http://127.0.0.1:8000/messages/?to_agent=core-hub&unread_only=true" \
| python3 -m json.tool
curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
-H "Content-Type: application/json" -d '{}'
```
Mark read when handled.
**Step 3 - Scan workplans**
**Step 3 — Scan workplans**
```bash
ls workplans/
```
For each file with `status: ready`, `active`, or `blocked`, note pending
`wait`/`todo`/`progress` tasks.
For each file with `status: ready`, `active`, or `blocked`, note pending `wait`/`todo`/`progress` tasks.
**Step 4 — Present brief**
**Step 4 - Work file-first**
1. **Active workplans** for `infotech` — title, task counts, blocking decisions
2. **Pending tasks** from `workplans/` + any `[repo:core-hub]` hub tasks
3. **Goal guidance** — if `goal_guidance` in summary:
- `needs_workplan`: surface as top action — *"Repo goal '{title}' has no workplan yet"*
- `alignment_warnings`: flag if active work is not aligned with current goal
4. **Suggested next action** — highest-priority open item
5. **SBOM status** — flag if `last_sbom_at` is unset for this repo
State Hub is a read/cache/index layer. Work structure belongs in repo files under ADR-001.
If no workplans: follow First Session Protocol (`first-session.md`).
**Session close**
**During work:** `record_decision()` · `add_progress_event()` · `resolve_decision()`
> State Hub is a *read model*. **Never register workplans or tasks by hand**
> (`create_workplan`, `create_task`) — write the workplan file in `workplans/`
> and run `fix-consistency`; C-06 registers the workplan and tasks and writes
> IDs back into the file. Manual registration creates duplicates when
> fix-consistency runs. Work structure belongs in repo files (ADR-001).
>
> Legacy: `create_workstream` and `/workstreams/` remain as metered aliases —
> see `workplan-convention.md` (compatibility footnote).
**Session close:**
With MCP tools:
```
add_progress_event(summary="...", topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a", workplan_id="<uuid>")
```
Without MCP tools:
```bash
cd ~/state-hub
make fix-consistency REPO=core-hub
curl -s -X POST http://127.0.0.1:8000/progress/ \
-H "Content-Type: application/json" \
-d '{"topic_id":"cee7bedf-2b48-46ef-8601-006474f2ad7a","event_type":"note","summary":"what changed","author":"codex"}'
-d '{"topic_id":"cee7bedf-2b48-46ef-8601-006474f2ad7a","workplan_id":"<uuid>","event_type":"note","summary":"what changed","author":"codex"}'
```
If workplan files were modified, ensure the local copy is up to date first,
then sync from the repo checkout:
```bash
git pull --ff-only
statehub fix-consistency
```
For repos where implementation runs on a remote machine (e.g. CoulombCore),
use the pull-before-fix mode from any shell with the State Hub CLI:
```bash
statehub fix-consistency --repo core-hub --remote
```
**C-15** (DB task ahead of file) is normal in multi-machine workflows — writeback
will sync the file to match DB. **C-16** (repo behind remote) blocks all writes
until you pull — intentional to prevent clobbering remote progress.

View file

@ -1,34 +1,35 @@
## Workplan Convention (ADR-001)
File location: `workplans/REPO-WP-NNNN-<slug>.md`
ID prefix: `REPO-WP-`
File location: `workplans/CORE-WP-NNNN-<slug>.md`
ID prefix: `CORE-WP-`
Work items originate as files in this repo **before** being registered in the hub.
Canonical workplan/workstream frontmatter statuses are:
Canonical workplan frontmatter statuses are:
`proposed`, `ready`, `active`, `blocked`, `backlog`, `finished`, `archived`.
Use `proposed` for a newly drafted plan, `ready` after review against current
repo state, and `finished` when implementation is complete. `stalled` and
`needs_review` are derived health labels, not stored statuses.
Closed workplans may be moved to `workplans/archived/` with a completion-date
prefix: `YYMMDD-REPO-WP-NNNN-<slug>.md`. The frontmatter id remains
prefix: `YYMMDD-CORE-WP-NNNN-<slug>.md`. The frontmatter id remains
unchanged; the prefix is only for quick visual reference.
Small opportunistic tasks discovered during another session use **Ad Hoc Tasks**:
`workplans/ADHOC-YYYY-MM-DD.md`, workstream slug `adhoc-YYYY-MM-DD`, and task ids
`workplans/ADHOC-YYYY-MM-DD.md`, workplan slug `adhoc-YYYY-MM-DD`, and task ids
`ADHOC-YYYY-MM-DD-T01`, `T02`, etc. Use adhocs only for low-risk work completed
directly. Promote anything requiring analysis, design, approval, dependencies, or
multiple planned phases into a normal workplan.
Ecosystem todos from other agents arrive as `[repo:repo-seed]` hub tasks —
visible at session start. Pick one up by creating the workplan file, then registering
the workstream.
Ecosystem todos from other agents arrive as `[repo:core-hub]` hub tasks —
visible at session start. Pick one up by creating the workplan file, committing,
and running `statehub fix-consistency` — C-06 registers the workplan in the hub.
Never register by hand with `create_workplan` (legacy MCP alias: `create_workstream`).
Task blocks use this shape:
```task
id: REPO-WP-NNNN-T01
id: CORE-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
@ -37,4 +38,18 @@ state_hub_task_id: "<uuid>" # written by fix-consistency — do not edit
Status progression is `todo``progress``done`; use `wait` for waiting or
blocked work and `cancel` for stopped work.
Workplan frontmatter carries `state_hub_workstream_id` — a legacy field name
kept for compatibility; it holds the hub workplan UUID and is written by
fix-consistency. Do not edit or rename it.
### Legacy terminology (compatibility footnote)
**Workplan** is the fleet term — see
`the-custodian/canon/standards/workplan-terminology-fleet_v0.1.md`.
**Workstream** is legacy only: some API routes (`/workstreams/`), params
(`workstream_id`), MCP aliases (`create_workstream`), and the frontmatter field
above remain until `STATE-WP-0069` retires them via legacy-meter. Treat those
identifiers as workplan IDs. Prefer `GET /workplans/` and `workplan_id` in new
examples and scripts.
<!-- Ralph Loop rules and HEUREKA sequence: ~/.claude/CLAUDE.md — do not duplicate here -->