Regenerate agent instructions: workstream -> workplan terminology

Registration guidance now prescribes file-first + fix-consistency (C-06)
instead of manual create_workplan/create_workstream calls; progress-event
examples use workplan_id; legacy field names annotated.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-02 01:47:46 +02:00
parent 491f50162d
commit 495a4fa7fb

View File

@@ -20,6 +20,12 @@ there is no MCP server for Codex agents.
|---------|-----|
| 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.
### Orient at session start
@@ -27,8 +33,8 @@ there is no MCP server for Codex agents.
# 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" \
# 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
@@ -51,12 +57,12 @@ curl -s -X POST http://127.0.0.1:8000/progress/ \
"summary": "what was done",
"event_type": "note",
"author": "codex",
"workstream_id": "<uuid>",
"workplan_id": "<uuid>",
"task_id": "<uuid>"
}'
```
Omit `workstream_id` / `task_id` when not applicable.
Omit `workplan_id` / `task_id` when not applicable.
### Update task status
@@ -80,7 +86,7 @@ curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
## Session Protocol
**Start:**
1. `cat .custodian-brief.md` — domain goal and open workstreams (offline-safe)
1. `cat .custodian-brief.md` — domain goal and open workplans (offline-safe)
2. Check inbox: `GET /messages/?to_agent=the-custodian&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`
@@ -92,12 +98,12 @@ curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
**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`:
3. After workplan file changes, run:
```bash
make fix-consistency REPO=the-custodian
statehub fix-consistency
```
This syncs task status from files into the hub DB.
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.
---
@@ -123,7 +129,7 @@ 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=the-custodian` is for coordination, not secret vending |
| **Claude Code** (MCP when available) | `get_domain_summary("custodian")` for workstreams; **still** use `warden route` for credential ownership |
| **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