key-cape/.claude/rules/session-protocol.md

Session Protocol

Dev Hub (State Hub API): http://127.0.0.1:8000 MCP server name in ~/.claude.json: dev-hub

Before production, credential or GitOps work read ~/the-custodian/docs/agent-environment-orientation.md; KeyCape specifics are in docs/operations.md, "Before any live change".

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="key-cape", 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=key-cape&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

1. Active workplans for infotech — title, task counts, blocking decisions
2. Pending tasks from workplans/ + any [repo:key-cape] 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 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 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:

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 key-cape --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.