The .claude/rules/ files still carried the seed placeholders. The practical failure: session-protocol.md told agents to check the inbox with to_agent="repo-seed", which returns [] regardless. Three unread messages from gate-house and risk-nexus sat unread for days behind that wrong query until fix-consistency's C-28 surfaced them. Replaced repo-seed with tenant-engine throughout, and REPO-WP- with this repo's actual TEN-WP- prefix. Also records that no MCP server is registered (dev-hub was deregistered 2026-09-04), so the REST paths are the default rather than the fallback, and fixes the root CLAUDE.md heading, still "Repo Seed". Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01HHwvAEQfmzLHtrFGhXtVjq Assistant: claude-code Assistant-Model: opus Assistant-Process: 823014@bnt-lap001 Assistant-Session: 2a0786b1-efea-4c38-959b-6e86a493f259
3.6 KiB
Session Protocol
Dev Hub (State Hub API): http://127.0.0.1:8000
Agent name on the hub (inbox to_agent): tenant-engine
No MCP server is registered by default (dev-hub was deregistered
2026-09-04). Use the REST paths below; the MCP variants apply only if a
server has been registered and is actually running.
Step 1 — Orient
Read the offline-safe brief first — it works without a live hub connection:
cat .custodian-brief.md
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:
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="tenant-engine", unread_only=True)
Mark read with mark_message_read(message_id). Reply or act on coordination
requests before proceeding.
Without MCP tools:
curl -s "http://127.0.0.1:8000/messages/?to_agent=tenant-engine&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
ls workplans/
For each file with status: ready, active, or blocked, note pending
wait/todo/progress tasks.
Step 4 — Present brief
- Active workplans for
infotech— title, task counts, blocking decisions - Pending tasks from
workplans/+ any[repo:tenant-engine]hub tasks - Goal guidance — if
goal_guidancein 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
- Suggested next action — highest-priority open item
- SBOM status — flag if
last_sbom_atis unset for this repo
If no workplans: follow First Session Protocol (first-session.md).
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 inworkplans/and runfix-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_workstreamand/workstreams/remain as metered aliases — seeworkplan-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:
curl -s -X POST http://127.0.0.1:8000/progress/ \
-H "Content-Type: application/json" \
-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:
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:
statehub fix-consistency --repo tenant-engine --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.