physics: bundles join their cluster; depth runs over the logical graph

Owner-approved brief (orchestrator, physics arc): two laws.

1. IMP-NODE CLUSTER ASSIGNMENT. Imp nodes were unclustered (the partition
   runs over stored propositions only) — no centroid pull, outside the
   painted hulls, bundles sitting on the periphery pointing outward.
   Now: a derived imp node's cluster is a function of its derivation —
   MAJORITY among its PREMISES' birth sessions (owner: premises, NOT the
   conclusion), ties to the chain's OWN birth (its provenance's first
   point — the asserting session; deterministic, coincides with the
   unanimous common case). Imp nodes are always re-derived, never
   birthed, so the assignment must be exactly this.

   Seam chosen: core/session-clusters.ts exports impClusterKey + a
   shared attachImpToCommunities that mutates a communities list's
   members IN PLACE. graphSnapshot attaches AFTER the hull filter (a
   2-proposition community + its bundle never resurrects a hull — the
   filter counts propositions); settleGraphLayout attaches to the
   unfiltered partition (settle pulls every community; hulls are a
   canvas-only concern). Both cluster-membership consumers — the sim's
   centroid pull and buildRegions' rasterization — read it through the
   members lists that went through the one helper, so the resting
   ledger and the live sim agree on where bundles belong.

2. DEPTHS OVER THE LOGICAL GRAPH. inferenceDepths ran Tarjan over the
   DRAWN edges (premise→imp→conclusion), inflating every multi-premise
   conclusion one hop (depth(imp)+1 instead of depth(premises)+1) and
   ranking the geometry point itself. Now:
   - deriveView additionally emits logicalEdges — every chain contracted
     to direct premise→conclusion arrows over PROPOSITION ids only
     (per-premise, deduped — a conclusion's rank is max over premises,
     which a single arbitrary premise edge could not express).
   - GraphSnapshot carries logicalEdges; createGraphSimulation /
     incrementalLayout accept a logicalEdges option: the depth
     machinery (orphan detection AND the rank pass) reads it, springs
     keep the drawn edges. Absent = edges (legacy behavior).
   - Imp nodes join the ORPHAN-EXEMPTION mask explicitly — never pinned
     to a level, keep the full regular forces (gravity, cluster pull,
     springs), settle naturally between premise and conclusion levels;
     the rank map is computed over propositions only, so arg_ ids are
     absent from it by construction.
   Wiring: settle + canvas (CanvasData.logicalEdges → buildSim) +
   replay-layout all pass the logical set.

   EXTRA FIX (in-slice discovery, one line, graph-server domain):
   server/graph.ts graphClusters — the practice picker's /api/graph/
   clusters — partitioned snap.NODES (the canvas image, imp nodes riding
   it since chains-primary), leaking arg_ ids into nodeIds: pickable ids
   that silently vanish inside chainsForSelection while nodeCount lied.
   Now partitions snap.propositions — same purity law as the chain
   table's 767a559 fix.

Tests (+13): impClusterKey pins (unanimous; cross-session majority; tie
→ chain's own birth, not the conclusion's); attach pins (members gain
the imp id, sorted; single-premise attaches nothing — no node exists;
dangling mints nothing; home absent from the list stays unattached);
snapshot pins (imp id rides cluster members to both consumers; the hull
filter counts propositions); logical-depth pins (multi-premise
conclusion at premises'+1 NOT +2; imp absent from the rank map);
depth-force exemption pin (rows pin crisply, arg_x floats unpinned —
old behavior stamped it onto the conclusion's row); deriveView logical
arrows (per-premise, deduped, proposition ids only).

src/server/graph.ts

@@ -33,7 +33,10 @@ export function graphView(): GraphSnapshot {
  *  honest, never guessed. A corrupt/empty graph is an empty list. */
 export function graphClusters(): GraphClusterGroup[] {
 	const snap = graphSnapshot(stores);
-	return birthSessionPartition(snap.nodes).map((group) => ({
+	// PROPOSITIONS ONLY: snap.nodes is the canvas image (imp nodes ride
+	// it); the picker offers propositions — an arg_ id in nodeIds would
+	// silently vanish inside chainsForSelection and lie about nodeCount.
+	return birthSessionPartition(snap.propositions).map((group) => ({
 		key: group.id,
 		kind: group.id in snap.sessions ? "chat" : "notes",
 		label: snap.sessions[group.id] ?? snap.fileSources[group.id] ?? null,