Refresh agent instruction files
Some checks failed
railiance-tests / smoke (push) Has been cancelled

This commit is contained in:
2026-05-18 16:55:49 +02:00
parent 8aeef483b7
commit 0c38343fc9
10 changed files with 381 additions and 175 deletions

184
CLAUDE.md
View File

@@ -1,177 +1,11 @@
# railiance-cluster — Claude Code Instructions
## Custodian State Hub Integration
This project is tracked as the **railiance** domain in the Custodian State Hub.
Hub topic ID: `ca369340-a64e-442e-98f1-a4fa7dc74a38`
The State Hub runs locally at http://127.0.0.1:8000. The MCP server (`state-hub`)
exposes tools for reading and writing state without touching the API directly.
---
### Session Protocol
**On receiving your first message — before writing any response text — execute
this orientation sequence. Do not greet, do not ask what to do first.**
**Step 1 — Call the State Hub**
```
get_state_summary() # orientation: workstreams, decisions, recent progress
get_next_steps() # contextual suggestions from resolved decisions
```
If the call fails, the API is offline: `cd ~/the-custodian/state-hub && make api`
**Step 2 — Scan local workplans**
Read every `.md` file under `workplans/`. Use `Glob(pattern="**/*.md", path="workplans/")`
or Bash `ls workplans/` to discover them. For each file with `status: active`,
extract and note:
- The workplan title and ID
- All tasks whose `status` is `todo` or `in_progress`
**Step 3 — Present orientation to the user**
Output a concise brief covering:
1. **Active workstreams** for the `railiance` domain — title, task counts,
any blocking decisions
2. **Pending tasks for this repo** — from local `workplans/` files (Step 2)
plus any state hub tasks with `[repo:railiance-cluster]` in their title
3. **Goal guidance** — if the summary contains a `goal_guidance` key, act on it:
- **`needs_workplan`** entries: for each active repo goal with no linked workstream,
surface it as the top suggested action — *"Repo goal '{title}' has no workplan yet.
Suggest: create workplans/RAIL-BS-WP-NNNN-<slug>.md and register a workstream
with repo_goal_id='{goal_id}'"*. Treat this as higher priority than continuing
existing work unless Bernd says otherwise.
- **`alignment_warnings`** entries: if active workstreams exist but are not linked
to the current repo goal, name the most recently active one and note:
*"Current work on '{recent_workstream_title}' may not be aligned with the active
goal '{active_goal_title}'. Continue unless you hear otherwise — but flag it."*
4. **Suggested next action** — the highest-priority open item across all sources,
with goal alignment taken into account
5. **SBOM status**`last_sbom_at` for `railiance-cluster` is currently null
(gap: no lockfile yet — see `workplans/RAIL-BS-WP-0001-dependency-management.md`)
**During work:**
- Use `record_decision()` for any decision that affects direction or dependencies.
- Use `add_progress_event()` for notable events (milestones, blockers, insights).
- Use `resolve_decision()` to close a decision once the choice is made.
> **Design boundary:** The State Hub is a *read model*. Two write operations are
> permanently sanctioned: **Resolving Decisions** and **Suggesting Next Steps**.
> Bootstrap tools are only for First Session Protocol. Work structure belongs
> in the domain repo as files (ADR-001).
**At the end of every session:**
- Call `add_progress_event()` with a summary of what was accomplished.
Include `topic_id: ca369340-a64e-442e-98f1-a4fa7dc74a38` and `workstream_id`.
---
### Known Pending Tasks (as of 2026-03-01)
**RAIL-BS-WP-0001 — Dependency Management** (`workplans/RAIL-BS-WP-0001-dependency-management.md`)
The SBOM scanner finds nothing to ingest because Ansible and control-node pip
dependencies are not declared in any lockfile. This is the top-priority open
task for this repo.
| Task | Priority | Status |
|------|----------|--------|
| T01: Audit control-node pip deps | medium | todo |
| T02: Create pyproject.toml + uv.lock | medium | todo |
| T03: Ingest SBOM into State Hub | medium | todo |
| T04: Create ansible/requirements.yml | low | todo |
State Hub task ID: `5f8cade5-119c-42e8-ba93-e9d0478650e4`
---
### First Session Protocol
Triggered when `get_state_summary()` shows **no workstreams** for `railiance`.
**Step 1** — Read `~/the-custodian/canon/projects/railiance/project_charter_v0.1.md`
and `roadmap_v0.1.md`, then scan this repo root.
**Step 2** — Survey in-progress work (TODOs, open branches, half-finished files).
**Step 3** — Propose 13 workstreams. Wait for approval before creating anything.
**Step 4** — Create workplan file first (`workplans/RAIL-WP-NNNN-<slug>.md`),
then register in hub:
```
create_workstream(topic_id="ca369340-a64e-442e-98f1-a4fa7dc74a38", ...)
create_task(workstream_id="<id>", ...)
```
**Step 5** — Record setup with `add_progress_event()`.
---
### Workplan Convention (ADR-001)
Work items originate as files in `workplans/` before being registered in the hub.
When the custodian creates a task for this repo, it places a workplan file here
AND creates a state hub task with `[repo:railiance-cluster]` in the title.
Both appear at session start via the orientation above.
---
### Contribution Tracking
```
contrib/
bug-reports/ # br-YYYY-MM-DD--org--repo--slug.md
feature-requests/ # fr-YYYY-MM-DD--org--repo--slug.md
extension-points/ # EP-RAIL-NNN--org--repo--slug.md
upstream-prs/ # upr-YYYY-MM-DD--org--repo--slug.md
```
Templates: `~/the-custodian/canon/standards/contrib-templates/`
---
### SBOM
After creating and committing the lockfile (see RAIL-BS-WP-0001), ingest:
```bash
cd ~/the-custodian/state-hub
make ingest-sbom REPO=railiance-cluster SCAN=1 REPO_PATH=/home/worsch/railiance-cluster
```
---
### Remote Execution & State Hub Tunnel
This repo is designed to be worked on **from the HostEurope server**. The
State Hub runs on Bernd's local workstation at `127.0.0.1:8000` and is not
publicly reachable — a reverse SSH tunnel must be open before starting a
remote session.
**On your local machine, before SSHing to the server:**
```bash
cd ~/the-custodian/state-hub
make tunnel HOST=tegwick@92.205.130.254
```
Keep that terminal open. Then SSH in normally from a second terminal.
**Verify the tunnel is live from the remote:**
```bash
curl http://127.0.0.1:8000/state/health
# expected: {"status":"ok"}
```
**If the tunnel is not up (degraded mode):**
- The `get_domain_summary` call in Step 1 will fail
- Skip Step 1 — proceed from local workplans only (Step 2)
- Log any progress events manually from the local machine after the session
---
### Quick Reference
`~/the-custodian/state-hub/mcp_server/TOOLS.md` — compact MCP tool reference
@SCOPE.md
@.claude/rules/repo-identity.md
@.claude/rules/session-protocol.md
@.claude/rules/first-session.md
@.claude/rules/workplan-convention.md
@.claude/rules/stack-and-commands.md
@.claude/rules/architecture.md
@.claude/rules/repo-boundary.md
@.claude/rules/agents.md