fix(template): rewrite session protocol to produce concrete orientation output

The previous template only defined a First Session Protocol (triggered when no
workstreams existed). When workstreams did exist, get_state_summary() was called
but no output was defined, causing registered-repo Claude sessions to produce
nothing useful.

New 3-step normal session protocol:
- Step 1: get_state_summary() + get_next_steps()
- Step 2: scan workplans/*.md for active tasks (todo/in_progress)
- Step 3: output orientation brief covering active workstreams, pending tasks
  for this repo (from workplans/ + [repo:<slug>] state hub tasks), suggested
  next action, and SBOM status

Also strengthens First Session Protocol, ADR-001 workplan convention section,
and SBOM ingest section (adds SCAN=1 REPO_PATH= flags).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-01 20:05:16 +01:00
parent 7df0152ca7
commit 82afb8d316

View File

@@ -8,69 +8,84 @@ Hub topic ID: `{TOPIC_ID}`
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 — call
`get_state_summary()` immediately.** Do not greet, do not ask what to do.
Call the tool first, then respond based on what you find.
**On receiving your first message — before writing any response text — execute
this orientation sequence. Do not greet, do not ask what to do first.**
**At the start of every session:**
1. Call `get_state_summary()` — orients you to active workstreams, blocking decisions,
and recent progress. If it fails, the API is likely offline:
```
cd ~/the-custodian/state-hub && make api
```
2. Call `get_next_steps()` — surfaces contextual suggestions from recently resolved
decisions and cleared workstream dependencies. Act on these before starting new work.
3. Check whether this domain has any open workstreams in the summary.
- **If workstreams exist:** review blocking decisions before starting work.
- **If no workstreams exist:** follow the First Session Protocol below.
**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 file matching `workplans/*.md` in this repo. For each one 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** (from state hub) for the `{DOMAIN}` 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:{REPO_SLUG}]` in their title
3. **Suggested next action** — the highest-priority open item across both sources
4. **SBOM status** — is `last_sbom_at` set for this repo? If not, note it as a gap
If there are no workstreams at all: follow the First Session Protocol below.
**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 — this is one
of the two sanctioned write operations in the hub.
- 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** (v0.2).
> The bootstrap tools (`create_workstream`, `create_task`, `update_task_status`) are
> only for First Session Protocol. Formal work structure — requirements, workplans,
> milestones, tasks — belongs in the domain repo, not managed through the hub.
> permanently sanctioned: **Resolving Decisions** and **Suggesting Next Steps**.
> The bootstrap tools (`create_workstream`, `create_task`, `update_task_status`)
> are only for First Session Protocol. Formal work structure — workplans, tasks —
> belongs in the domain repo as files (ADR-001), not managed through the hub alone.
**At the end of every session:**
- Call `add_progress_event()` with a summary of what was accomplished or decided.
Include `topic_id: {TOPIC_ID}` and the relevant `workstream_id`.
---
### First Session Protocol
Triggered when `get_state_summary()` shows **no workstreams** for the `{DOMAIN}` topic.
This means the project is registered but work has not yet been structured.
Triggered when `get_state_summary()` shows **no workstreams** for the `{DOMAIN}`
topic. The project is registered but work has not yet been structured.
**Step 1 — Understand the project (read, don't write)**
- `canon/projects/{DOMAIN}/project_charter_v0.1.md` — purpose, scope, success criteria
- `canon/projects/{DOMAIN}/roadmap_v0.1.md` — planned phases
- Scan the repo root: README, directory structure, any existing code or docs
- `~/the-custodian/canon/projects/{DOMAIN}/project_charter_v0.1.md` — purpose, scope
- `~/the-custodian/canon/projects/{DOMAIN}/roadmap_v0.1.md` — planned phases
- Scan the repo root: README, directory structure, existing code or docs
**Step 2 — Survey in-progress work**
- Look for TODOs, open branches, half-finished files, or notes
- Look for TODOs, open branches, half-finished files, notes
- Note what is already done vs. what is clearly started but incomplete
**Step 3 — Propose workstreams to Bernd**
Based on what you found, propose 13 workstreams. Each workstream should be:
- A coherent strand of work lasting weeks to months (not a single task)
- Named clearly enough that its scope is obvious
- Anchored to a phase in the roadmap if possible
Propose 13 workstreams — each a coherent strand of work lasting weeks to months,
named clearly, anchored to a roadmap phase. **Wait for approval before creating.**
Present the proposals and **wait for approval before creating anything**.
**Step 4 — Create and populate (after approval)**
**Step 4 — Create workplan file first, then DB record**
Per ADR-001, work items originate as files in the repo:
```
workplans/<DOMAIN>-WP-NNNN-<slug>.md ← write this first
```
Then register in the hub:
```
create_workstream(topic_id="{TOPIC_ID}", title="...", owner="...", description="...")
create_task(workstream_id="<id>", title="...", priority="high|medium|low")
# repeat for each task in the workstream
```
Aim for 37 tasks per workstream at this stage. Tasks should be concrete and actionable.
**Step 5 — Record the setup**
```
@@ -82,12 +97,28 @@ add_progress_event(
)
```
---
### Workplan Convention (ADR-001)
Work items MUST originate as files in this repo before being registered in the hub.
**File location:** `workplans/<ID>-<slug>.md`
**Frontmatter required:** `id`, `type: workplan`, `domain`, `repo`, `status`,
`state_hub_workstream_id`, `state_hub_task_id` (per task)
When the custodian creates a task targeting this repo from another session, it:
1. Creates a state hub task with `[repo:{REPO_SLUG}]` in the title
2. Creates a workplan file in this repo's `workplans/`
3. You will see both at session start via the orientation sequence above
---
### Contribution Tracking
This project tracks upstream contributions in `contrib/` — bug reports, feature
requests, extension-point proposals, and upstream PRs — as canonical Markdown files.
Track upstream contributions in `contrib/` — bug reports (BR), feature requests
(FR), extension-point proposals (EP), upstream PRs (UPR).
**Directory layout:**
```
contrib/
bug-reports/ # br-YYYY-MM-DD--org--repo--slug.md
@@ -99,46 +130,27 @@ contrib/
Templates: `~/the-custodian/canon/standards/contrib-templates/`
Convention: `~/the-custodian/canon/standards/contribution-convention_v0.1.md`
**Register a contribution in the State Hub:**
```
register_contribution(
type="upr", # br | fr | ep | upr
title="Add injectTocTop to Observable Framework",
target_org="observablehq",
target_repo="framework",
body_path="contrib/upstream-prs/2026-02-26--observablehq--framework--inject.md",
related_workstream_id="<uuid>",
)
```
**Update status when upstream responds:**
```
register_contribution(type="br|fr|ep|upr", title="...", target_org="...",
target_repo="...", body_path="contrib/...", related_workstream_id="<uuid>")
update_contribution_status(contribution_id="<uuid>", status="submitted")
# then: acknowledged → accepted → merged
```
**List all contributions for this domain:**
```
get_contributions(target_repo="framework")
```
---
### SBOM
Software Bill of Materials for this repo is tracked in the State Hub.
**Ingest the current lockfile:**
After updating dependencies, re-ingest the SBOM:
```bash
cd ~/the-custodian/state-hub
make ingest-sbom REPO={REPO_SLUG}
make ingest-sbom REPO={REPO_SLUG} SCAN=1 REPO_PATH=$(pwd)
```
**Check licence risk:**
```
get_licence_report()
```
Check compliance: `http://localhost:3000/repos`
Standard: `~/the-custodian/canon/standards/sbom-convention_v0.1.md`
**View SBOM dashboard:** `http://localhost:3000/sbom`
---
### Quick Reference
See `~/the-custodian/state-hub/mcp_server/TOOLS.md` for a compact tool reference.
`~/the-custodian/state-hub/mcp_server/TOOLS.md` compact MCP tool reference