Graph pipeline cost metrics: capture naming spend, fold all channels, cost pill + panel

- Cluster namer bills the money channel now: per-step usage + model
  captured via onStep, persisted as NamingRunUsage records to
  data/graph/naming-runs.jsonl (idempotent per startedAt; failed/aborted
  runs persist too — money spent either way). callUsage promoted to
  extraction.ts module scope for reuse.
- core/cost-summary.ts: the pure fold behind the pill — chat runs,
  notes-source runs, and naming runs into stage totals (extraction /
  audit / naming) + newest-first recent runs. Dollars INFERRED read-time
  via prices.ts, never stored; unpriced models excluded-but-counted
  (render '—', never a silent zero); tokens always sum.
- GET /api/graph/costs (src/server graphCosts composition, thin route).
- Graph view: bottom-left cost pill (cumulative dollars headline) +
  expandable breakdown panel (stage rows with tokens secondary, recent
  runs with time/title/merged/cost); fetched on mount, refetched when a
  pipeline run finishes; merged into one bottom-left stack with the
  running-pipeline pills.
- Tests: pure-fold suite, naming capture wiring (full importNotes ->
  naming path), store idempotency + strict reads.

src/core/contracts/graph.ts

@@ -20,7 +20,7 @@
 /** Two relations only (DECIDED 2026-09-02): follows = b is derivable from a;
  *  supports = a grounds b without entailing it. No scalars, no encoded
  *  strength — strength is derived at read time from topology. */
-import type { ExtractionRunUsage } from "./chat.ts";
+import type { CallUsage, ExtractionRunUsage } from "./chat.ts";
 
 export type EdgeType = "follows" | "supports";
 
@@ -65,6 +65,41 @@ export interface NotesSource {
 	extractions?: ExtractionRunUsage[];
 }
 
+/** What one cluster-naming refresh did — the namer's ClusterRefreshStats,
+ *  contract-shaped so the agent layer needs no contracts import.
+ *  Structural twins stay interchangeable. */
+export interface NamingRunStats {
+	/** Communities the current graph divides into (all sizes). */
+	detected: number;
+	/** Communities that kept a label via core-survival. */
+	claimed: number;
+	/** Communities sent to the namer (unnamed, size >= MIN_CLUSTER_SIZE). */
+	named: number;
+	/** Labeling records actually appended (idempotent dedupe may shrink). */
+	appended: number;
+}
+
+/** One cluster-naming run's usage record — the money channel's THIRD stage
+ *  (graph cost metrics, 2026-09). The namer is graph-global (tied to no
+ *  chat or source), so runs live in their own append-only ledger
+ *  (config.LEDGER_FILES.namingRuns). Appended when a run actually called
+ *  the model; skipped refreshes (nothing to name) never bill and never
+ *  append. Idempotent per startedAt — same discipline as every usage
+ *  channel. Cost is INFERRED at read time from steps + model
+ *  (core/prices.ts) — dollars are never stored. */
+export interface NamingRunUsage {
+	/** ms epoch — the idempotency key. */
+	startedAt: number;
+	/** ISO — wall-clock time of the run. */
+	at: string;
+	durationMs: number;
+	/** The labeler role's model id. */
+	model: string;
+	/** Every billed call (usually ONE — the namer is single-submit). */
+	steps: CallUsage[];
+	stats: NamingRunStats;
+}
+
 export interface GraphNode {
 	/** Opaque stable id, store-assigned: "n_" + nanoid-like. */
 	id: string;