feat(client): read-model surface — open/sync + anchorless union sparql_query

Proven against the real broker (probe): opening docs then a single anchorless `sparql_query` with a `GRAPH ?g { ... }` body reads the LOCAL UNION of all synced named graphs — the fast, hang-free replacement for the reactive-ORM per-document fan-out (which aborted on any unsynced/fresh repo → 75s never-fires). New `read-model.ts` (readUnion) exposes this; there is no reactive union query, so listing is one-shot and consumers re-query on change. docs/read-model.md refined with the probe finding (an explicit `GRAPH ?g` body iterates all named graphs regardless of the anchor; the anchor only bounds the default graph). 93 tests pass; tsc rc=0. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-05 18:20:09 +02:00
parent 5acc07a7e3
commit e24f52749f
4 changed files with 281 additions and 0 deletions
@@ -18,6 +18,8 @@ export * as inbox from "./inbox";
 export * as discovery from "./discovery";
 export type { IndexEntry, SubmitOptions } from "./discovery";
 export * as docs from "./docs";
+export * as readModel from "./read-model";
+export type { UnionSubject } from "./read-model";
 export * as storeRegistry from "./store-registry";
 export type { AccountRecord, RegistrySession } from "./store-registry";
 export * as isolation from "./isolation";
@@ -0,0 +1,144 @@
+/**
+ * read-model — the LISTING primitive of the polyfill: open/sync a set of
+ * documents, then run ONE anchorless union `sparql_query` over the LOCAL UNION
+ * and return the triples grouped per subject. This is the mechanism documented
+ * in docs/read-model.md, verified against the real broker (T03.k probe): a
+ * `GRAPH ?g { ?s ?p ?o }` body with NO anchor spans every graph currently opened
+ * in the session store.
+ *
+ * ── WHY not the reactive ORM fan-out ──────────────────────────────────────
+ * `useShape({ graphs: […manyDocs] })` drives `orm_start_graph` over a fan-out of
+ * per-entity graphs; a freshly-created / not-yet-synced doc in that fan-out makes
+ * `RepoNotFound` abort the whole subscription → the readyPromise never resolves →
+ * the ~75s hang (docs/nextgraph-current-state.md § The ORM fan-out hang). Listing
+ * MUST instead be a one-shot union `sparql_query`. There is no reactive union
+ * query, so reactivity is assembled by RE-QUERYING on a change signal.
+ *
+ * ── The two steps ─────────────────────────────────────────────────────────
+ * 1. OPEN/SYNC the docs. A repo is only in the union once opened into the
+ *    session's oxigraph store. Opening is done PER-DOC via an anchored probe
+ *    query (`resolveTargetForSparql(anchor)` opens that one repo) — per-doc, so a
+ *    single unreachable doc fails in isolation instead of aborting a fan-out.
+ * 2. UNION QUERY. One anchorless `SELECT ?g ?s ?p ?o WHERE { GRAPH ?g { ?s ?p ?o } }`
+ *    over the local union; group rows by subject.
+ *
+ * ── GENERIC by construction ───────────────────────────────────────────────
+ * Zero application domain here: the consumer passes the doc NURIs to open (from
+ * the discovery index for public events, or its own scope docs for my-entities)
+ * and interprets the returned per-subject property bags. All NextGraph I/O routes
+ * through the T01.a `docs` primitives (the REAL injected `ng`), so this module
+ * imports no `@ng-org` package.
+ *
+ * At migration the union query is unchanged (native SPARQL union over the wallet);
+ * only the "open/sync" step swaps to opening real per-user store repos by cap.
+ */
+
+import { docCreate, sparqlUpdate, sparqlQuery } from "./docs";
+import { getStoreRegistryDeps } from "./polyfill";
+import { assertNuri } from "./sparql";
+import type { Nuri } from "./types";
+
+// Keep the primitives referenced so tree-shaking never drops the import used by
+// the (side-effecting) open step below; `docCreate`/`sparqlUpdate` are not used
+// here but the module intentionally depends only on the docs primitive surface.
+void docCreate;
+void sparqlUpdate;
+
+/** One subject read from the union, with its properties (predicate → values). */
+export interface UnionSubject {
+  /** The subject IRI (`?s`). */
+  subject: string;
+  /** The graph the subject was read from (`?g` — the repo graph name). */
+  graph: string;
+  /** predicate IRI → the list of object values (literals or IRIs) for it. */
+  props: Record<string, string[]>;
+}
+
+/** Tolerant extraction of SPARQL SELECT bindings across possible shapes. */
+function bindings(
+  result: unknown,
+): Array<Record<string, { value: string } | undefined>> {
+  if (!result) return [];
+  if (Array.isArray(result))
+    return result as Array<Record<string, { value: string }>>;
+  const anyRes = result as {
+    results?: { bindings?: Array<Record<string, { value: string }>> };
+  };
+  return anyRes.results?.bindings ?? [];
+}
+
+async function sessionId(): Promise<string> {
+  return (await getStoreRegistryDeps().getSession()).sessionId;
+}
+
+/**
+ * Open/sync ONE doc into the session store by running a cheap anchored probe
+ * query against it (`resolve_target_for_sparql(anchor)` opens that repo). Per-doc
+ * and tolerant: a doc that can't be opened (not yet synced, no cap) throws HERE,
+ * in isolation, and is skipped — it never aborts the listing of the others (the
+ * fan-out ORM's failure mode). Returns whether the open succeeded.
+ */
+async function openDoc(sid: string, doc: Nuri): Promise<boolean> {
+  try {
+    const nuri = assertNuri(doc);
+    // ASK is the cheapest way to touch (hence open) the repo; the result is
+    // irrelevant — the side effect (repo opened into the union) is the point.
+    await sparqlQuery(sid, "ASK { ?s ?p ?o }", undefined, nuri);
+    return true;
+  } catch (error) {
+    console.error("[read-model] open failed for", doc, error);
+    return false;
+  }
+}
+
+/**
+ * OPEN/SYNC a set of docs, then read the LOCAL UNION with ONE anchorless
+ * `sparql_query`, grouped per subject. `docs` are the NURIs to bring into the
+ * union (the consumer resolves them by need — index for public, own scope docs
+ * for mine). Docs that fail to open are skipped (see {@link openDoc}).
+ *
+ * The union query is anchorless (`anchor` undefined → LOCAL UNION) with an
+ * explicit `GRAPH ?g { ?s ?p ?o }` body, so it spans every opened graph and
+ * attributes each row to its source graph.
+ */
+export async function readUnion(docs: Nuri[]): Promise<UnionSubject[]> {
+  const sid = await sessionId();
+  const unique = [...new Set(docs.filter(Boolean))];
+  // 1. OPEN/SYNC — per-doc, tolerant (a bad doc never aborts the whole list).
+  await Promise.all(unique.map((d) => openDoc(sid, d)));
+
+  if (unique.length === 0) return [];
+
+  // 2. UNION QUERY — ONE anchorless query over the local union. The union spans
+  // ALL opened graphs (including the shim/inbox internals), so constrain it to
+  // the requested subjects with a VALUES block. In the polyfill each entity's
+  // subject IRI IS its own document NURI (writeEntity uses the doc NURI as the
+  // subject), so the requested doc NURIs ARE the subjects to read — precise and
+  // independent of the repo_graph_name overlay suffix on ?g.
+  const values = unique.map((d) => `<${assertNuri(d)}>`).join(" ");
+  const query =
+    `SELECT ?g ?s ?p ?o WHERE { GRAPH ?g { ?s ?p ?o . VALUES ?s { ${values} } } }`;
+  let rows: Array<Record<string, { value: string } | undefined>> = [];
+  try {
+    rows = bindings(await sparqlQuery(sid, query, undefined, undefined));
+  } catch (error) {
+    console.error("[read-model] union query failed:", error);
+    return [];
+  }
+
+  const bySubject = new Map<string, UnionSubject>();
+  for (const row of rows) {
+    const s = row.s?.value;
+    const p = row.p?.value;
+    const o = row.o?.value;
+    const g = row.g?.value ?? "";
+    if (!s || !p || o === undefined) continue;
+    let entry = bySubject.get(s);
+    if (!entry) {
+      entry = { subject: s, graph: g, props: {} };
+      bySubject.set(s, entry);
+    }
+    (entry.props[p] ??= []).push(o);
+  }
+  return [...bySubject.values()];
+}