fix(#93): apply Williams-bound budgets consistently

- FullNeighborRecalc now derives maxNeighbors from computeNeighborMaxDegree
  instead of using a fixed default of 16
- Query.ts uses getResidentCount() as proxy for corpus size to avoid
  scanning all pages on the hot path for computeSubgraphBounds

Closes #93

Co-authored-by: devlux76 <[email protected]>

Author: Copilot

lib/cortex/Query.ts

@@ -191,16 +191,16 @@ export async function query(
 
   // --- Subgraph expansion ---
   // Use dynamic Williams-derived bounds unless the caller has pinned an
-  // explicit maxHops value.  Only load all pages when we actually need to
-  // compute bounds — skip the full-page scan on the hot path when maxHops is
-  // already known.
+  // explicit maxHops value.  Prefer the hotpath resident count as an efficient
+  // proxy for corpus size to avoid scanning all pages on the hot path.
   const topPageIds = topPages.map((p) => p.pageId);
   let effectiveMaxHops: number;
   if (options.maxHops !== undefined) {
     effectiveMaxHops = options.maxHops;
   } else {
-    const allPages = await metadataStore.getAllPages();
-    effectiveMaxHops = computeSubgraphBounds(allPages.length).maxHops;
+    const residentCount = await metadataStore.getResidentCount();
+    const graphMass = residentCount > 0 ? residentCount : combinedPageIds.size;
+    effectiveMaxHops = computeSubgraphBounds(Math.max(1, graphMass)).maxHops;
   }
   const subgraph = await metadataStore.getInducedNeighborSubgraph(topPageIds, effectiveMaxHops);
 

lib/daydreamer/FullNeighborRecalc.ts

@@ -14,7 +14,7 @@
 // ---------------------------------------------------------------------------
 
 import type { Hash, MetadataStore, SemanticNeighbor, Page, VectorStore } from "../core/types";
-import { computeCapacity, DEFAULT_HOTPATH_POLICY, type HotpathPolicy } from "../core/HotpathPolicy";
+import { computeCapacity, computeNeighborMaxDegree, DEFAULT_HOTPATH_POLICY, type HotpathPolicy } from "../core/HotpathPolicy";
 import { batchComputeSalience, runPromotionSweep } from "../core/SalienceEngine";
 
 // Minimum pair budget per idle recalc cycle.
@@ -31,7 +31,8 @@ export interface FullNeighborRecalcOptions {
   metadataStore: MetadataStore;
   vectorStore: VectorStore;
   policy?: HotpathPolicy;
-  /** Maximum semantic neighbors stored per page. Default: 16. */
+  /** Maximum semantic neighbors stored per page.
+   *  When omitted, uses Williams-derived `computeNeighborMaxDegree(graphMass)`. */
   maxNeighbors?: number;
   /** Current timestamp (ms since epoch). Defaults to Date.now(). */
   now?: number;
@@ -84,7 +85,6 @@ export async function runFullNeighborRecalc(
     metadataStore,
     vectorStore,
     policy = DEFAULT_HOTPATH_POLICY,
-    maxNeighbors = 16,
     now = Date.now(),
   } = options;
 
@@ -110,6 +110,9 @@ export async function runFullNeighborRecalc(
   const totalGraphMass = (await metadataStore.getAllPages()).length;
   const pairBudget = Math.max(MIN_RECALC_PAIR_BUDGET, computeCapacity(totalGraphMass, policy.c));
 
+  // Derive max neighbor degree from Williams bounds if not explicitly provided.
+  const maxNeighbors = options.maxNeighbors ?? computeNeighborMaxDegree(totalGraphMass, policy.c);
+
   let totalVolumesProcessed = 0;
   let totalPagesProcessed = 0;
   let totalPairsComputed = 0;