Refresh agent instruction files

This commit is contained in:
2026-05-18 16:55:47 +02:00
parent de984736ca
commit d949f3e93e
10 changed files with 334 additions and 100 deletions

20
.claude/rules/agents.md Normal file
View File

@@ -0,0 +1,20 @@
## Kaizen Agents
Specialized agent personas available on demand via the state-hub MCP.
**Discover:** `list_kaizen_agents()` — returns all agents with name, description, category
**Load:** `get_kaizen_agent("tdd-workflow")` — returns full instructions; read and follow them
Common agents:
| Agent | Category | When to use |
|-------|----------|-------------|
| `tdd-workflow` | testing | Step-by-step TDD8 workflow for any feature |
| `code-refactoring` | quality | Code quality analysis and safe refactoring |
| `test-maintenance` | testing | Diagnose and fix failing tests |
| `requirements-engineering` | process | Prevent interface/mock mismatches upfront |
| `keepaTodofile` | process | Maintain TODO.md during work |
| `project-management` | process | Track status, determine next steps |
| `datamodel-optimization` | quality | Optimize dataclasses and data structures |
All 17 agents: call `list_kaizen_agents()` for the full list.

View File

@@ -1,38 +1,8 @@
## Architecture
OpsBridge has two logical components:
**1. OpsBridge — tunnel lifecycle manager** (this repo)
Manages named SSH reverse tunnels defined in `~/.config/bridge/tunnels.yaml`.
Each tunnel runs in a subprocess with a reconnect backoff loop; PIDs are tracked
in `~/.local/state/bridge/`. Bridge states: `stopped → starting → connected →
degraded → failed`. The `degraded` state means SSH is up but the optional HTTP
health check is failing.
**2. OpsCatalog — operations knowledge repository** (planned extension)
A Git-backed YAML catalog of operations domains, targets, bridges, and actor
classes. OpsBridge consumes this catalog to resolve bridge identifiers and
orient operators. Schema examples are in `wiki/OpsCatalogSpecification.md`.
The catalog layout follows: `opscatalog/domains/<domain>/{domain.yaml,
targets/, bridges/, docs/}`.
Key design constraints:
- OpsBridge owns lifecycle management only; it does not own credential issuance or CA
operations (those belong to `ops-warden`)
- Each tunnel is identified by name (e.g. `state-hub-coulombcore`); names used
in config, CLI args, and log filenames must stay consistent
- Actor attribution is tracked per bridge using the three-actor vocabulary from the
AccessManagementDirective: `adm` (human), `agt` (LLM agent), `atm` (automation);
actor names must carry the matching prefix (`adm-*`, `agt-*`, `atm-*`) (FRS §5.7)
- Two credential modes are first-class and must remain independently functional:
1. **Static key mode** (default) — `ssh_key` only; no TTL, no cert logic
2. **cert_command mode** — a pluggable shell command that issues a CA-signed cert
before each SSH launch; TTL parsed from the cert; pre-emptive refresh ~5 min
before expiry; `cert_identity` logged in every `BRIDGE_CONNECTED` event
Specification docs are in `wiki/`: PRD (`OpsBridgePrd.md`), FRS
(`OpsBridgeFrs.md`), and OpsCatalog spec (`OpsCatalogSpecification.md`).
<!-- TODO: Describe the key design decisions and component structure.
Key modules, data flows, external integrations, state machines, etc. -->
## Quick Reference
`~/the-custodian/state-hub/mcp_server/TOOLS.md`
`~/state-hub/mcp_server/TOOLS.md` — MCP tool reference

View File

@@ -0,0 +1,38 @@
## First Session Protocol
Triggered when `get_domain_summary("custodian")` shows **no workstreams**.
The project is registered but work has not yet been structured.
**Step 1 — Read, don't write**
- `~/the-custodian/canon/projects/custodian/project_charter_v0.1.md` — purpose, scope
- `~/the-custodian/canon/projects/custodian/roadmap_v0.1.md` — planned phases
- Scan repo root: README, directory structure, existing code or docs
**Step 2 — Survey in-progress work**
Look for TODOs, open branches, half-finished files. Note done vs. started but incomplete.
**Step 3 — Propose workstreams to Bernd**
Propose 13 workstreams — each a coherent strand, weeks to months, anchored to a
roadmap phase. **Wait for approval before creating.**
**Step 4 — Create workplan file first, then DB record (ADR-001)**
```
workplans/ops-bridge-WP-NNNN-<slug>.md ← write this first
```
Then register in the hub:
```
create_workstream(topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a", title="...", owner="...", description="...")
create_task(workstream_id="<id>", title="...", priority="high|medium|low")
```
**Step 5 — Record the setup**
```
add_progress_event(
summary="First session: structured custodian into N workstreams, M tasks",
event_type="milestone",
topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a",
detail={"workstreams": [...], "tasks_created": M}
)
```
<!-- Delete or archive this file once past first session -->

View File

@@ -1,6 +1,8 @@
## Repo boundary
This repo owns **tunnel lifecycle management only**. It does not own:
- State hub code → `the-custodian/state-hub/`
- SSH key management → `railiance-infra/` (S1) or user dotfiles
- Ansible/provisioning`railiance-infra/`
This repo owns **ops-bridge** only. It does not own:
<!-- TODO: List what belongs in adjacent repos, e.g.:
- SSH key management → railiance-infra/
- State hub code → state-hub/
-->

View File

@@ -1,7 +1,5 @@
**Purpose:** SSH reverse tunnel lifecycle manager. Keeps remote execution
environments (COULOMBCORE, Railiance nodes) connected to the local Custodian
State Hub so Claude Code sessions on those machines have full MCP connectivity.
**Purpose:** SSH reverse tunnel lifecycle manager. Keeps remote execution environments (COULOMBCORE, Railiance nodes) connected to the local state hub. Small CLI tool: bridge up/down/status/logs per named tunnel config.
**Domain:** custodian
**Repo slug:** ops-bridge
**Repo ID:** 1bf99f56-6e94-4379-a9ea-295a4c181889
**Topic ID:** cee7bedf-2b48-46ef-8601-006474f2ad7a

View File

@@ -1,38 +1,84 @@
## Custodian State Hub Integration
## Session Protocol
State Hub: http://127.0.0.1:8000
### Session Protocol
**Step 0 — Tunnel health**
Before anything else:
```bash
bridge status
```
Bring up any stopped or stale tunnels before accessing remote services.
**Step 1 — Orient**
Read the offline-safe brief first:
Read the offline-safe brief first — it works without a live hub connection:
```bash
cat .custodian-brief.md
```
Then call the MCP tool for richer context (skip if unreachable):
Then call the MCP tool for richer cross-domain context when MCP tools are exposed:
```
get_domain_summary("custodian")
```
**Step 2 — Scan workplans**
If MCP tools are unavailable in the current agent session, use the REST API:
```bash
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**
With MCP tools:
```
get_messages(to_agent="ops-bridge", 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=ops-bridge&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 '{}'
```
**Step 3 — Scan workplans**
```bash
ls workplans/
```
For each file with `status: ready`, `active`, or `blocked`, note pending
`todo`/`in_progress` tasks.
**During work:** use `record_decision()`, `add_progress_event()`, `resolve_decision()`.
**Step 4 — Present brief**
**Session close:** `add_progress_event()` with workstream_id.
1. **Active workstreams** for `custodian` — title, task counts, blocking decisions
2. **Pending tasks** from `workplans/` + any `[repo:ops-bridge]` 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
If workplan files were modified, run from `~/the-custodian/state-hub/`:
```bash
make fix-consistency REPO=ops-bridge
If no workstreams: follow First Session Protocol (`first-session.md`).
**During work:** `record_decision()` · `add_progress_event()` · `resolve_decision()`
> State Hub is a *read model*. Bootstrap tools (`create_workstream`, `create_task`)
> are First Session Protocol only. Work structure belongs in repo files (ADR-001).
**Session close:**
With MCP tools:
```
add_progress_event(summary="...", topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a", workstream_id="<uuid>")
```
Without MCP tools:
```bash
curl -s -X POST http://127.0.0.1:8000/progress/ \
-H "Content-Type: application/json" \
-d '{"topic_id":"cee7bedf-2b48-46ef-8601-006474f2ad7a","workstream_id":"<uuid>","event_type":"note","summary":"what changed","author":"codex"}'
```
If workplan files were modified, ensure the local copy is up to date first:
```bash
git -C <repo_path> pull --ff-only
cd ~/state-hub && make fix-consistency REPO=ops-bridge
```
For repos where implementation runs on a remote machine (e.g. CoulombCore),
use the combined target which pulls before fixing:
```bash
cd ~/state-hub && make fix-consistency-remote REPO=ops-bridge
```
**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

@@ -1,46 +1,19 @@
## What this repo builds
A CLI tool (`bridge`) that manages named SSH reverse tunnels:
```
bridge up [TUNNEL] # start tunnel(s)
bridge down [TUNNEL] # stop tunnel(s)
bridge restart [TUNNEL] # restart tunnel(s)
bridge status # show all tunnels: state, uptime, last health check
bridge logs [TUNNEL] # tail reconnect log
```
Config file: `~/.config/bridge/tunnels.yaml`
Each tunnel:
- Named (e.g. `state-hub-coulombcore`)
- Reverse SSH port-forward: `ssh -R remote_port:127.0.0.1:local_port host`
- Auto-reconnects on drop (backoff loop)
- Optional HTTP health check to confirm the forwarded service is reachable
PRD: `workplans/BRIDGE-WP-0001-initial-implementation.md`
## Stack
- **Language:** Python 3.11+
- **CLI framework:** Typer
- **Dependencies:** typer, pyyaml, httpx
- **Packaging:** `uv tool install` (single command install, no venv activation)
- **No system daemons** — process management is internal, PID tracked in
`~/.local/state/bridge/`
<!-- TODO: Fill in language, frameworks, and key dependencies -->
- **Language:**
- **Key deps:**
## Dev Commands
```bash
# Install locally for development
uv tool install -e .
# TODO: Fill in the standard commands for this repo
# Install dependencies
# Run tests
uv run pytest
# Run a single test
uv run pytest tests/test_tunnel.py::test_name -v
# Lint / type check
# Lint
uv run ruff check .
# Build / package (if applicable)
```

View File

@@ -1,6 +1,28 @@
### Workplan Convention (ADR-001)
## Workplan Convention (ADR-001)
File location: `workplans/BRIDGE-WP-NNNN-<slug>.md`
Prefix: `BRIDGE-WP`
File location: `workplans/ops-bridge-WP-NNNN-<slug>.md`
ID prefix: `OPS-WP`
<!-- Ralph Loop rules are defined globally in ~/.claude/CLAUDE.md — do not duplicate here -->
Work items originate as files in this repo **before** being registered in the hub.
Canonical workplan/workstream 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-ops-bridge-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
`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:ops-bridge]` hub tasks —
visible at session start. Pick one up by creating the workplan file, then registering
the workstream.
<!-- Ralph Loop rules and HEUREKA sequence: ~/.claude/CLAUDE.md — do not duplicate here -->

162
AGENTS.md Normal file
View File

@@ -0,0 +1,162 @@
# ops-bridge — Agent Instructions
## Repo Identity
**Purpose:** SSH reverse tunnel lifecycle manager. Keeps remote execution environments (COULOMBCORE, Railiance nodes) connected to the local state hub. Small CLI tool: bridge up/down/status/logs per named tunnel config.
**Domain:** custodian
**Repo slug:** ops-bridge
**Topic ID:** `cee7bedf-2b48-46ef-8601-006474f2ad7a`
**Workplan prefix:** `OPS-WP-`
---
## State Hub Integration
The Custodian State Hub tracks work across all domains. Interact via HTTP REST —
there is no MCP server for Codex agents.
| Context | URL |
|---------|-----|
| Local workstation | `http://127.0.0.1:8000` |
| Remote via tunnel | `http://127.0.0.1:18000` |
### Orient at session start
```bash
# Offline brief — works without hub connection
cat .custodian-brief.md
# Active workstreams for this domain
curl -s "http://127.0.0.1:8000/workstreams/?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=ops-bridge&unread_only=true" \
| python3 -m json.tool
```
Mark a message read:
```bash
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)
```bash
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",
"workstream_id": "<uuid>",
"task_id": "<uuid>"
}'
```
Omit `workstream_id` / `task_id` when not applicable.
### Update task status
```bash
curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
-H "Content-Type: application/json" \
-d '{"status": "in_progress"}'
# values: todo | in_progress | done | blocked
```
### Flag a task for human review
```bash
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 workstreams (offline-safe)
2. Check inbox: `GET /messages/?to_agent=ops-bridge&unread_only=true`; mark read
3. Scan workplans: `ls workplans/` — note `status: ready`, `active`, or `blocked` files and open tasks
4. Check blocked 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. Log: `POST /progress/` with a summary of what changed
3. Note for the custodian operator: after workplan file changes, run from
`~/state-hub`:
```bash
make fix-consistency REPO=ops-bridge
```
This syncs task status from files into the hub DB.
---
## 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/OPS-WP-NNNN-<slug>.md`
**Archived location:** finished workplans may move to
`workplans/archived/YYMMDD-OPS-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` with task ids `ADHOC-YYYY-MM-DD-T01`, etc. Use
this only for low-risk work completed directly; create a normal workplan for
anything needing analysis, design, approval, dependencies, or multiple phases.
**Frontmatter:**
```yaml
---
id: OPS-WP-NNNN
type: workplan
title: "..."
domain: custodian
repo: ops-bridge
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>" # written by fix-consistency — do not edit
---
```
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.
**Task block format** (one per `##` section):
```
## Task Title
` ` `task
id: OPS-WP-NNNN-T01
status: todo | in_progress | done | blocked
priority: high | medium | low
state_hub_task_id: "<uuid>" # written by fix-consistency — do not edit
` ` `
Task description text.
```
Status progression: `todo` → `in_progress` → `done` (or `blocked`)
To create a new workplan:
1. Write the file following the format above
2. Notify the custodian operator to run `make fix-consistency REPO=ops-bridge`
(or send a message to the hub agent via `POST /messages/`)

View File

@@ -1,8 +1,11 @@
# ops-bridge — Claude Code Instructions
@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