JSON records
Rows live in JSONB with a GIN index. Relationships are a relation table. Required and unique constraints are validated before insert. No DDL, no migration risk — and it already delivers permanent storage.
The generative UI protocol is versioned, validated on the server, and closed by construction. An agent describes components — never HTML — and the server renders them with the same design system, the same translation catalogue and the same authorization as every other view.
{
"protocol": "gsdui/1",
"canvas_id": "…",
"base_version": 12,
"layout_title": { "i18n": "ui.canvas.sales_breakdown" },
"view_mode": "GEN_UI",
"widgets": []
}
view_mode is one of GEN_UI, BROWSER,
DIFF or LOGS. The enum matches the UI exactly — an earlier
draft listed four modes in the UI and three in the schema.
| Rule | Consequence |
|---|---|
| Rows are records keyed by column | Column reorder cannot corrupt data. Positional arrays are not allowed. |
| Actions resolve server-side | The client never supplies code, and the server never trusts the client's copy of a widget. |
| The component whitelist is closed | Unknown types and unknown props are rejected at validation. |
| Patches are RFC 7386 merge patches | One widget's props change without touching the rest of the canvas. |
| Text deltas are ephemeral | The final assembled message is appended once as a TEXT event; deltas are never persisted. |
A widget carrying inline rows is a screenshot with more steps. Instead, a widget may carry a binding to a dataset, and the server resolves it as the viewer.
{
"id": "w_sales_table",
"type": "DataTable",
"state_key": "sales.by_region",
"props": {
"columns": [
{ "key": "region", "label": { "i18n": "ui.table.region" }, "type": "text" },
{ "key": "volume", "label": { "i18n": "ui.table.volume" }, "type": "currency" }
],
"data": {
"dataset": "…",
"parameters": { "period": "$param.period", "team": "$param.team" }
}
}
}
Rows live in JSONB with a GIN index. Relationships are a relation table. Required and unique constraints are validated before insert. No DDL, no migration risk — and it already delivers permanent storage.
High-volume models get a real table. The DDL is generated from validated field metadata only, identifiers are slug-derived and pattern-checked, and the change is gated by human approval.
An idempotent command applies controlled DDL on every deploy. Destructive operations are never automatic, and a drift check fails CI when the registry, generated models and live columns disagree.
There is one Django template per widget type. A UI mutation carries the rendered fragment plus props and a sequence number, and the client swaps it in place.
{% trans %} authoritative — the translation catalogue stays the source of truth.This is the acceptance criterion. The rule for reviewing the design is simple: if a step needs a concept the domain model does not have, the model is wrong — not the scenario.
Northwind is the organization. Sales is a team. APAC Pipeline is a room.
Dana is the organization owner. Sam leads Sales. Priya belongs to a guest organization with a room share.
analyst has an OpenAI-compatible default runtime and a CLI fallback, is rostered into the room as its default agent, and is owned by Dana.
Deals live in a dynamic model. Sam defines the dataset deals.by_region with period and team.
Definitions are data. The registry is the durable source of truth for schemas, and it is what lets an organization model its own domain without a deploy.
A named bundle an organization owns.
A schema versioned against a storage tier: JSON by default, physical as an approval-gated opt-in.
A typed field — text, integer, decimal, boolean, date, datetime, JSON, or a relation to another model.
The first four roadmap steps are built: ASGI, the actor flag, the organization event log and the topic WebSocket consumer — plus a working workspace and a CLI agent over the Agent Client Protocol.
The socket reconnects with backoff and re-subscribes from the last sequence. Visibility and online events re-subscribe to catch up. A stale page cannot hide behind a dead socket.
Token chunks arrive as transient deltas into a streaming bubble. The persisted final message replaces it. A mid-stream reload loses partial text by design — the final message is the record.
The composer hides model choice unless the message mentions a rostered agent, so a plain room note never changes the topic model. A switch appends an event and renders in the timeline.
The ACP client negotiates session options: one CLI accepts a set_model call, the other implements only the standard config option. One client serves both, with a fallback on method-not-found.
An agent process receives only PATH, HOME, USER, SHELL, locale, terminal and the XDG directories. The server's database URL, Redis URL and secret key are deliberately withheld, and a test pins it.
A missing binary, a crash before the handshake and a hang each record an error event that names the cause and the evidence. Before this, a failed run looked like the agent ignoring you.
Still ahead: approvals, secrets and per-capability grants; the canvas and the full protocol; the JSON API; the worker and the executor placements; and the product layer of objectives, tasks, artifacts and datasets.