Birth-session clustering + the prober graph-tools data seam (wave 7 chunk A)

Embeddings are dying (chunk B removes the machinery); the clusters they
used to carry become the session that created them — derived on read.

- New src/core/session-clusters.ts: birthSessionPartition groups merged
  nodes by their FIRST SURVIVING provenance point's chatId (owner-locked
  2026-09-23). Deletion is self-healing by construction: stripped-birth
  survivors re-attribute to their earliest remaining contributor, and
  empty-provenance nodes stay unclustered. Notes imports are birth-sessions
  too (owner ruling) — their label is the file path.
- graphSnapshot: clusters = the birth partition filtered >= MIN_CLUSTER_SIZE
  (the hull presentation rule), id = session id, label = session name (chat
  title / file path; a deleted record renders unlabeled). The persisted
  cluster-labelings join dies; no LLM naming pass needed anymore.
- settleGraphLayout derives the same partition from readNodes — drops its
  readEmbeddings dep. One cluster concept everywhere.
- Prober data seam (core/graph.ts, pure ports-driven like the snapshot):
  graphSessionIndex (every birth session: id, name, chat|file kind,
  createdAt/updatedAt, birth-proposition count, recency-ordered) and
  graphSessionPropositions (a session's birth propositions with the
  extractor's latest understanding level and THAT event's own timestamp —
  owner ruling: quiz outcomes are ledger evidence, they never move the
  evaluation date). Teacher's tool handlers consume these in-process.
- New agent.graphTools subsection { enabled?: boolean } (owner ruling:
  the toggle gates prober tool REGISTRATION — agent capability, agent
  section, its own subsection, NOT the tool-toggles map; absent = ON).
  Lenient sanitizer, strict settings-body parser, passthrough resolution,
  and graphToolsEnabled(effective) = graph.enabled && toggle for Teacher's
  registry wiring.

Gates: tsc clean, eslint clean, 923/923 tests, next build compiles.
Live-verified on the worktree dev data: 10 nodes → 2 clusters labeled
with their chat titles; session index + propositions carry levels and
their own timestamps.

src/core/graph.ts

@@ -51,8 +51,10 @@ import type {
 	GraphSnapshot,
 	LedgerEvent,
 	LedgerEventKind,
+	UnderstandingLevel,
 } from "./contracts.ts";
-import { matchClusterLabelings, MIN_CLUSTER_SIZE } from "./clusters.ts";
+import { MIN_CLUSTER_SIZE } from "./clusters.ts";
+import { birthSessionPartition } from "./session-clusters.ts";
 import type { QuestionAnswerData } from "./question-core.ts";
 import type { ChatStore, GraphStore } from "./ports.ts";
 
@@ -496,23 +498,20 @@ export function graphSnapshot(deps: GraphDeps): GraphSnapshot {
 		(nodeObservations[nodeId] ??= {})[chatId] = note;
 	}
 
-	// Semantic topic communities (DECIDED 2026-09-13, replacing structural
-	// Louvain): average-linkage clustering over embeddings — related
-	// topics, not reasoning chains. Edge-orphans join topics by meaning;
-	// stragglers stay loose (filtered at the presentation threshold
-	// below). The partition is computed ONCE per embedding batch by the
-	// embedder (the agglomerative pass is ~1.5s at current scale) and
-	// PERSISTED in the embedding ledger — reads just load it. Nodes whose
-	// embedding hasn't landed yet simply sit unclustered until the next
-	// read after the embedder runs.
-	const communities = deps.graphStore.readEmbeddings().clusters;
-	const claims = matchClusterLabelings(communities, deps.graphStore.readClusterLabels());
+	// BIRTH-SESSION CLUSTERS (wave 7, owner-locked 2026-09-23): embeddings
+	// are dead — a cluster is the SESSION THAT CREATED ITS PROPOSITIONS,
+	// derived on read from provenance (core/session-clusters.ts). The label
+	// is the session's NAME (chat title / file path): no LLM naming pass, no
+	// persisted partition to invalidate. MIN_CLUSTER_SIZE stays the hull
+	// presentation rule (a region needs >= 3 propositions for a hull). A
+	// birth session whose record is gone (deleted chat) keeps its members
+	// but renders unlabeled — honest, never guessed.
+	const communities = birthSessionPartition(nodes);
 	const clusters: Cluster[] = communities
-		.map((community, index) => ({ community, claim: claims[index] }))
-		.filter(({ community }) => community.members.length >= MIN_CLUSTER_SIZE)
-		.map(({ community, claim }) => ({
-			id: claim?.id ?? clusterContentId(community.members),
-			label: claim?.label ?? null,
+		.filter((community) => community.members.length >= MIN_CLUSTER_SIZE)
+		.map((community) => ({
+			id: community.id,
+			label: sessions[community.id] ?? fileSources[community.id] ?? null,
 			members: community.members,
 		}));
 
@@ -533,5 +532,118 @@ export function graphSnapshot(deps: GraphDeps): GraphSnapshot {
 	};
 }
 
+// ─── Prober graph tools — the data seam (wave 7, owner-locked 2026-09-23) ───
+
+/** One session in the prober's graph view: every provenance anchor the
+ *  graph can name — a real chat (deep-linkable) or an imported notes file
+ *  (owner ruling 2026-09-23: files are birth-sessions too, kind "file").
+ *  The prober's session-list tool renders these; the per-session view is
+ *  graphSessionPropositions below. Pure derivation over the same ports
+ *  the snapshot reads — Teacher's tool handlers call these in-process. */
+export interface GraphSessionEntry {
+	/** chatId or notes source id ("src_…") — the birth-session key. */
+	id: string;
+	/** The chat's title, or the file's path — the cluster label's source. */
+	name: string;
+	/** A real chat (its record still exists) or an imported notes file. */
+	kind: "chat" | "file";
+	/** When the session began: the chat's createdAt, or the file's
+	 *  importedAt. null when no record can date it. */
+	createdAt: string | null;
+	/** Most recent activity: the chat's updatedAt, or the file's
+	 *  importedAt. null when no record can date it. */
+	updatedAt: string | null;
+	/** How many propositions were BORN in this session (birth-session
+	 *  clustering's count — shared/re-encountered nodes count for their
+	 *  birth session only). */
+	propositions: number;
+}
+
+/** The prober's session list: every birth session, most-recently-active
+ *  first (undatable records sink, in stable id order). */
+export function graphSessionIndex(deps: GraphDeps): GraphSessionEntry[] {
+	const counts = new Map<string, number>();
+	for (const cluster of birthSessionPartition(getGraph(deps.graphStore).nodes)) {
+		counts.set(cluster.id, cluster.members.length);
+	}
+	const chats = new Map(deps.chatStore.listChats().map((chat) => [chat.id, chat]));
+	const sources = new Map(deps.graphStore.readSources().map((s) => [s.id, s]));
+	const entries: GraphSessionEntry[] = [];
+	for (const [id, propositions] of counts) {
+		const chat = chats.get(id);		if (chat) {
+			entries.push({
+				id,
+				name: chat.title,
+				kind: "chat",
+				createdAt: chat.createdAt,
+				updatedAt: chat.updatedAt,
+				propositions,
+			});
+			continue;
+		}
+		const source = sources.get(id);
+		entries.push({
+			id,
+			name: source?.filePath ?? id,
+			kind: "file",
+			createdAt: source?.importedAt ?? null,
+			updatedAt: source?.importedAt ?? null,
+			propositions,
+		});
+	}
+	return entries.sort(
+		(a, b) =>
+			(b.updatedAt ?? "").localeCompare(a.updatedAt ?? "") ||
+			(b.createdAt ?? "").localeCompare(a.createdAt ?? "") ||
+			(a.id < b.id ? -1 : 1),
+	);
+}
+
+/** One birth proposition of one session, for the prober's per-session
+ *  view. `understanding` is the extractor's latest observation for
+ *  (node, session) — the named-word scale (solid/shaky/accepted/resisted/
+ *  not yet engaged) — and `evaluatedAt` is THAT event's own timestamp
+ *  (owner ruling 2026-09-23: quiz outcomes are evidence in the ledger,
+ *  but they never move the evaluation date — the level's event does). */
+export interface GraphSessionProposition {
+	nodeId: string;
+	/** The compact handle — the same name the canvas shows. */
+	name: string;
+	understanding: UnderstandingLevel | null;
+	/** The `at` of the event that minted `understanding`; null when the
+	 *  session never evaluated this proposition. */
+	evaluatedAt: string | null;
+}
+
+/** The propositions BORN in one session, with the session's latest
+ *  understanding of each. Latest observation wins by `at`, then by
+ *  ledger order (the same tie rule the snapshot's nodeObservations
+ *  uses). Members sorted by node id — deterministic. */
+export function graphSessionPropositions(deps: GraphDeps, sessionId: string): GraphSessionProposition[] {
+	const born = getGraph(deps.graphStore).nodes.filter(
+		(node) => node.provenance[0] !== undefined && node.provenance[0]!.chatId === sessionId,
+	);
+	const latest = new Map<string, { at: string; note: string; index: number }>();
+	deps.graphStore.readEvents().forEach((event, index) => {
+		if (event.kind !== "observation" || event.nodeId === null || event.chatId !== sessionId) return;
+		if (!event.note) return;
+		const current = latest.get(event.nodeId);
+		if (!current || event.at > current.at || (event.at === current.at && index > current.index)) {
+			latest.set(event.nodeId, { at: event.at, note: event.note, index });
+		}
+	});
+	return born
+		.map((node) => {
+			const observation = latest.get(node.id);
+			return {
+				nodeId: node.id,
+				name: node.name,
+				understanding: (observation?.note as UnderstandingLevel | undefined) ?? null,
+				evaluatedAt: observation?.at ?? null,
+			};
+		})
+		.sort((a, b) => (a.nodeId < b.nodeId ? -1 : 1));
+}
+
 // Re-export: the contract owns the shape; legacy importers still reach it.
 export type { EmissionStats };

src/core/layout-settle.ts

@@ -1,5 +1,6 @@
-import type { EmbeddingsLedger, GraphEdge, GraphNode } from "./contracts.ts";
+import type { GraphEdge, GraphNode } from "./contracts.ts";
 import { incrementalLayout } from "./layout.ts";
+import { birthSessionPartition } from "./session-clusters.ts";
 import type { Position } from "./contracts.ts";
 
 /**
@@ -11,17 +12,16 @@ import type { Position } from "./contracts.ts";
  * finish before the next /api/graph fetch reflects the change.
  *
  * SPLIT FROM layout.ts deliberately (2026-09-13): layout.ts is in the
- * browser barrel, and the settle needs the Louvain partition for the
- * cluster centroid pull — the heavy deps must not ship in the client
- * bundle. Server code imports this module DIRECTLY; it is never
- * re-exported through src/core/index.ts.
+ * browser barrel, and the settle needs the cluster partition for the
+ * cluster centroid pull — this module must not ship in the client bundle.
+ * Server code imports it DIRECTLY; it is never re-exported through
+ * src/core/index.ts.
  */
 export function settleGraphLayout(graphStore: {
 	readNodes(): GraphNode[];
 	readEdges(): GraphEdge[];
 	readPositions(): Record<string, Position>;
 	writePositions(positions: Record<string, Position>): void;
-	readEmbeddings(): EmbeddingsLedger;
 }): void {
 	const nodes = graphStore.readNodes();
 	if (nodes.length === 0) return;
@@ -34,11 +34,12 @@ export function settleGraphLayout(graphStore: {
 	});
 	const edges = graphStore.readEdges();
 	const previous = new Map(Object.entries(graphStore.readPositions()));
-	// The cluster partition for the centroid pull: the SAME persisted
-	// semantic topics the snapshot renders (computed by the embedder
-	// once per batch, stored in the embedding ledger) — one cluster
-	// concept everywhere.
-	const communities = graphStore.readEmbeddings().clusters;
+	// The cluster partition for the centroid pull: the SAME birth-session
+	// partition the snapshot renders (derived from provenance on read —
+	// core/session-clusters.ts, wave 7) — one cluster concept everywhere.
+	// The unique list is the deduped set the partition needs (lines may
+	// repeat an id — first defines).
+	const communities = birthSessionPartition(unique);
 	const next = incrementalLayout(unique, edges, previous, { clusters: communities });
 	graphStore.writePositions(Object.fromEntries(next));
 }

src/core/session-clusters.ts

@@ -0,0 +1,73 @@
+/**
+ * BIRTH-SESSION CLUSTERING (wave 7, owner-locked 2026-09-23): embeddings
+ * are dead — a proposition's cluster is the SESSION THAT CREATED IT,
+ * derived deterministically from provenance. Cluster labels are session
+ * names (the chat title or the imported file's path): no model call, no
+ * key, no configuration. What the agglomerative pass grouped by MEANING
+ * proximity, this groups by WHERE KNOWLEDGE WAS BORN — the owner's call
+ * that the session that minted a set of propositions is the honest
+ * "region of the world model" they belong to.
+ *
+ * Birth session (owner ruling 2026-09-23): a node's FIRST surviving
+ * provenance point's chatId — the create line's first point at read time
+ * (getGraph merges lines by id, first line defines, provenance unions in
+ * line order — so provenance[0] is the birth point of the surviving
+ * lines). This makes deletion self-healing with ZERO special handling:
+ * delete-nodes strips a session's create lines and its provenance points;
+ * a SURVIVING shared node re-attributes to its earliest remaining
+ * contributor (provenance[0] walks forward), and a node left with NO
+ * provenance at all is simply unclustered. The partition is derived on
+ * every read — there is no persisted partition to invalidate.
+ *
+ * Notes imports are birth-sessions too (owner ruling 2026-09-23): their
+ * nodes carry a "src_…" source id instead of a chat id; the caller labels
+ * them with the file's path (kind: file in the session views).
+ *
+ * Browser-safe pure logic (no node builtins, no fs): same contract style
+ * as the rest of the core graph derivation. Not re-exported through the
+ * core barrel — the shell reads clusters from the snapshot; only the
+ * server-side derivations (snapshot, settle) and tests import this.
+ */
+import type { GraphNode } from "./contracts.ts";
+
+/** One birth-session cluster: the session id + the SORTED member node
+ *  ids born in it. The shape is deliberately the { members } contract
+ *  the layout consumer takes; `id` rides along for consumers that need
+ *  the session identity (the snapshot's cluster id + label join). */
+export interface BirthSessionCluster {
+	/** The birth session's id — a chatId or a notes source id ("src_…"). */
+	id: string;
+	/** Node ids born in this session, sorted. */
+	members: string[];
+}
+
+/** A node's birth session: its first surviving provenance point's chatId,
+ *  or null when the node carries no provenance at all (unclustered). */
+export function birthSessionOf(node: GraphNode): string | null {
+	const first = node.provenance[0];
+	return first === undefined ? null : first.chatId;
+}
+
+/**
+ * The birth-session partition over the given node LINES: dedupes by id
+ * (first line defines — the getGraph rule), groups by birth session, and
+ * returns the groups size-desc with members sorted (deterministic output:
+ * ties break by session id ascending). Nodes with no surviving provenance
+ * are left unclustered — they belong to no session the graph can name.
+ */
+export function birthSessionPartition(nodes: readonly GraphNode[]): BirthSessionCluster[] {
+	const members = new Map<string, string[]>();
+	const seen = new Set<string>();
+	for (const node of nodes) {
+		if (seen.has(node.id)) continue;
+		seen.add(node.id);
+		const birth = birthSessionOf(node);
+		if (birth === null) continue;
+		const bucket = members.get(birth);
+		if (bucket) bucket.push(node.id);
+		else members.set(birth, [node.id]);
+	}
+	return [...members.entries()]
+		.map(([id, list]) => ({ id, members: [...list].sort() }))
+		.sort((a, b) => b.members.length - a.members.length || (a.id < b.id ? -1 : 1));
+}

src/core/settings-resolution.ts

@@ -81,6 +81,9 @@ export interface EffectiveSettings {
 		 *  passthrough delta — engine resolution (pin → auto → unavailable)
 		 *  lives in server/search.ts, where keys are visible. */
 		search: { engine?: SearchEngineId };
+		/** Prober graph tools (wave 7): passthrough delta as stored —
+		 * absent/undefined enabled = ON; consumers use graphToolsEnabled. */
+		graphTools: { enabled?: boolean };
 	};
 	/** The resolved strong/cheap/vision slots: each tier's concrete model or
 	 *  NULL when the tier holds no model (no factory floor — BYOK all the
@@ -178,6 +181,7 @@ export function resolveSettings(record: UserSettings | null): EffectiveSettings
 			tools: agent.tools ?? {},
 			prompts: agent.prompts ?? {},
 			search: agent.search ?? {},
+			graphTools: agent.graphTools ?? {},
 		},
 		models: {
 			strong: resolveSlot(modelsSection.strong),
@@ -228,3 +232,17 @@ export function extractionEnabled(graph: Required<GraphSettings>): boolean {
 export function graphContextEnabled(graph: Required<GraphSettings>): boolean {
 	return graph.enabled && graph.embedding;
 }
+
+/**
+ * The PROBER GRAPH TOOLS gate (wave 7, owner ruling 2026-09-23): the
+ * toggle is an agent-capability switch (it gates tool registration), but
+ * the tools only mean anything when the graph itself runs — so the
+ * effective gate composes the graph master switch AND the toggle.
+ * Teacher's tool factories consume this at registration time.
+ */
+export function graphToolsEnabled(effective: {
+	graph: Required<GraphSettings>;
+	agent: { graphTools: { enabled?: boolean } };
+}): boolean {
+	return effective.graph.enabled && (effective.agent.graphTools.enabled ?? true);
+}

src/core/settings.ts

@@ -200,6 +200,14 @@ export interface AgentSettings {
 	 *  engine must still have its key, else search is honestly unavailable.
 	 *  Absent + no key = unavailable (no silent fallback, no default). */
 	search?: { engine?: SearchEngineId };
+	/** Prober graph tools (wave 7, owner ruling 2026-09-23): read-only
+	 *  knowledge-graph views for the prober agent — a session list +
+	 *  per-session propositions with understanding levels. Its SUBJECT
+	 *  is the graph but its MECHANISM is agent capability (tool
+	 *  registration), so it lives here in its OWN subsection, not in the
+	 *  tool-toggles map. Absent = enabled (the toggle discipline); the
+	 *  effective gate composes graph.enabled AND this switch. */
+	graphTools?: { enabled?: boolean };
 	/** System-prompt override SWITCHES keyed by segment path (absent key =
 	 *  off). Switch-on requires the override file to exist (enforced by the
 	 *  route); the switch is explicit so users keep a file on disk but run
@@ -419,6 +427,14 @@ function sanitizeAgent(raw: Record<string, unknown>): AgentSettings {
 		const engine = (raw.search as Record<string, unknown>).engine;
 		if (engine === "tavily" || engine === "brave") out.search = { engine };
 	}
+	// Prober graph tools (wave 7): its own agent-section subsection —
+	// lenient read side (a bad shape drops the key and the default ON
+	// resumes; the write side's parser is strict).
+	if (raw.graphTools !== null && typeof raw.graphTools === "object" && !Array.isArray(raw.graphTools)) {
+		const enabled = (raw.graphTools as Record<string, unknown>).enabled;
+		if (enabled === undefined) out.graphTools = {};
+		else if (typeof enabled === "boolean") out.graphTools = { enabled };
+	}
 	return out;
 }
 

src/server/settings-body.ts

@@ -195,6 +195,18 @@ export function parseAgentSettingsBody(body: unknown): SettingsBodyResult<AgentS
 			settings.search = { engine: search.engine };
 		}
 	}
+	// Prober graph tools (wave 7, owner ruling 2026-09-23): an agent-section
+	// subsection, not a tool-toggles key — the mechanism is agent capability
+	// (tool registration), the subject is the graph. Strict write side:
+	// object shape only; `enabled` boolean when present. Absent = ON.
+	if (raw.graphTools !== undefined) {
+		const graphTools = asRecord(raw.graphTools);
+		if (!graphTools) return { ok: false, error: "graphTools must be an object" };
+		if (graphTools.enabled !== undefined && typeof graphTools.enabled !== "boolean") {
+			return { ok: false, error: "graphTools.enabled must be a boolean" };
+		}
+		settings.graphTools = graphTools.enabled === undefined ? {} : { enabled: graphTools.enabled };
+	}
 	return { ok: true, settings };
 }