diff --git a/scripts/eval-quality.ts b/scripts/eval-quality.ts
index 52cbc50f2d..96475014ce 100644
--- a/scripts/eval-quality.ts
+++ b/scripts/eval-quality.ts
@@ -753,6 +753,7 @@ async function runRetrievalQualityCases(args: {
         topK: testCase.topK,
         minSimilarity: 0.12,
         skipCache: true,
+        forceEmbedding: testCase.forceEmbedding,
       }),
     );
     const latencyMs =
diff --git a/scripts/eval-retrieval.ts b/scripts/eval-retrieval.ts
index 0a4332f2f0..7218ae7319 100644
--- a/scripts/eval-retrieval.ts
+++ b/scripts/eval-retrieval.ts
@@ -19,6 +19,10 @@ const goldenCaseSchema = z.object({
   expectedContentTerms: z.array(contentExpectationSchema).default([]),
   topK: z.number().int().positive().default(8),
   expectTableEvidence: z.boolean().default(false),
+  // Bypass the lexical text-fast-path so this case always exercises the embedding/vector
+  // index. Use for "vector-*" probes that would otherwise be answered by a lexical shortcut,
+  // so a re-index's effect on vector retrieval is actually measured.
+  forceEmbedding: z.boolean().optional(),
 });
 
 const goldenCasesSchema = z.array(goldenCaseSchema);
@@ -37,6 +41,7 @@ type EvalArgs = {
   caseTimeoutMs: number;
   p90BudgetMs: number;
   p50BudgetMs: number;
+  forceEmbedding: boolean;
 };
 
 export type GoldenRetrievalResult = {
@@ -116,6 +121,7 @@ function parseArgs(argv: string[]): EvalArgs {
     caseTimeoutMs: inferredMode === "latency" ? 25_000 : 0,
     p90BudgetMs: 20_000,
     p50BudgetMs: 8_000,
+    forceEmbedding: false,
   };
 
   for (let index = 0; index < argv.length; index += 1) {
@@ -138,6 +144,10 @@ function parseArgs(argv: string[]): EvalArgs {
       if (args.caseTimeoutMs <= 0) args.caseTimeoutMs = 25_000;
       continue;
     }
+    if (token === "--force-embedding") {
+      args.forceEmbedding = true;
+      continue;
+    }
 
     const value = argv[index + 1];
     if (!value || value.startsWith("--")) throw new Error(`Missing value for ${token}`);
@@ -743,6 +753,7 @@ async function main() {
         topK: testCase.topK,
         minSimilarity: 0.12,
         skipCache: args.mode !== "latency",
+        forceEmbedding: testCase.forceEmbedding || args.forceEmbedding,
       }),
     );
     const searchOutcome = await withCaseTimeout(searchPromise, args.caseTimeoutMs);
diff --git a/scripts/fixtures/rag-retrieval-golden.json b/scripts/fixtures/rag-retrieval-golden.json
index b31176b768..34b5d4f368 100644
--- a/scripts/fixtures/rag-retrieval-golden.json
+++ b/scripts/fixtures/rag-retrieval-golden.json
@@ -224,5 +224,108 @@
     ],
     "topK": 12,
     "expectTableEvidence": true
+  },
+  {
+    "id": "vector-ptsd",
+    "query": "How is post-traumatic stress disorder managed in a person with intrusive flashbacks, nightmares, hyperarousal and avoidance after a traumatic event?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Traumatic Stress"],
+    "expectedContentTerms": [["trauma", "traumatic", "ptsd", "flashback"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-ocd",
+    "query": "How is obsessive-compulsive disorder managed in a person with distressing intrusive obsessions and repetitive compulsive rituals?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Obsessive"],
+    "expectedContentTerms": [["obsess", "compuls", "intrusive", "ocd"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-panic",
+    "query": "How is panic disorder managed in a person with recurrent unexpected panic attacks, palpitations and anticipatory anxiety?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Panic"],
+    "expectedContentTerms": [["panic", "attack", "anxiety"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-anorexia",
+    "query": "How is anorexia nervosa managed in a person with severe dietary restriction, intense fear of weight gain and body-image disturbance?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Anorexia"],
+    "expectedContentTerms": [["anorexia", "eating", "weight"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-gad-worry",
+    "query": "How is a patient managed who has persistent, excessive worry about many everyday things that they find very hard to control, along with restlessness and muscle tension?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Generalised Anxiety"],
+    "expectedContentTerms": [
+      ["worry", "anxiety", "generalised"],
+      ["cbt", "ssri", "snri", "antidepressant", "psychotherapy"]
+    ],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-tourette",
+    "query": "How is Tourette syndrome managed in a child with chronic motor tics and vocal tics?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Tourette"],
+    "expectedContentTerms": [["tic", "tics", "tourette"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-postnatal",
+    "query": "How is postnatal (postpartum) depression managed in a new mother who develops low mood and poor bonding with her infant in the first weeks postpartum?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Postnatal"],
+    "expectedContentTerms": [["postnatal", "postpartum", "perinatal", "depression"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-bipolar",
+    "query": "How is bipolar disorder managed in an adult with recurrent episodes of mania and depression?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Bipolar"],
+    "expectedContentTerms": [["bipolar", "mania", "manic", "mood"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-adhd",
+    "query": "How is attention deficit hyperactivity disorder managed in an adult with inattention, distractibility and impulsivity?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Attention Deficit Hyperactivity"],
+    "expectedContentTerms": [["attention", "adhd", "hyperactiv", "impuls"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
+  },
+  {
+    "id": "vector-opioid",
+    "query": "How is opioid use disorder managed in a person dependent on heroin?",
+    "expectedQueryClass": "broad_summary",
+    "expectedDocumentSubstrings": ["Opioid Use Disorder"],
+    "expectedContentTerms": [["opioid", "heroin", "opiate", "methadone", "buprenorphine"]],
+    "topK": 8,
+    "expectTableEvidence": false,
+    "forceEmbedding": true
   }
 ]
diff --git a/src/lib/rag.ts b/src/lib/rag.ts
index 6764accd2a..1620405c6e 100644
--- a/src/lib/rag.ts
+++ b/src/lib/rag.ts
@@ -307,6 +307,10 @@ export type SearchChunksArgs = {
   // Internal: set when this call is a re-run on a trigram-corrected query, to prevent the
   // unsupported-short-circuit typo-correction path from recursing more than once.
   typoCorrected?: boolean;
+  // Diagnostic/eval-only: bypass every lexical text-fast-path so retrieval always exercises
+  // the embedding/vector stage. Lets the golden eval measure the vector index directly for a
+  // re-index, instead of being masked by lexical shortcuts. Never set on production paths.
+  forceEmbedding?: boolean;
 };
 
 export type AnswerProgressEvent = {
@@ -1429,7 +1433,7 @@ function stableHash(value: string) {
 export function retrievalPlanCacheQuery(
   args: Pick<
     SearchChunksArgs,
-    "query" | "documentId" | "documentIds" | "ownerId" | "queryMode" | "topK" | "minSimilarity"
+    "query" | "documentId" | "documentIds" | "ownerId" | "queryMode" | "topK" | "minSimilarity" | "forceEmbedding"
   >,
   queryClass?: RagQueryClass,
   queryVariants: string[] = [],
@@ -1445,6 +1449,7 @@ export function retrievalPlanCacheQuery(
     `topK:${args.topK ?? 8}`,
     `min:${args.minSimilarity ?? 0.15}`,
     `rag:${ragDeepMemoryVersion}`,
+    `force:${args.forceEmbedding ? 1 : 0}`,
   ].join("|");
   return queryCacheKeyForStorage(cacheKey);
 }
@@ -5516,7 +5521,7 @@ export async function searchChunksWithTelemetry(args: SearchChunksArgs) {
     });
 
     const baseTextFastPath = decideTextFastPath(args.query, baseTextResults, queryClassification.queryClass);
-    if (shouldReturnBeforeMemory(queryClassification.queryClass, baseTextFastPath)) {
+    if (!args.forceEmbedding && shouldReturnBeforeMemory(queryClassification.queryClass, baseTextFastPath)) {
       textFastResults = await attachPageVisualEvidence(supabase, baseTextResults);
       textFastResults = applySecondStageRerankIfNeeded({
         queryClass: queryClassification.queryClass,
@@ -5567,7 +5572,7 @@ export async function searchChunksWithTelemetry(args: SearchChunksArgs) {
     telemetry.rerank_latency_ms += Date.now() - rerankStartedAt;
 
     const boostedTextFastPath = decideTextFastPath(args.query, textFastResults, queryClassification.queryClass);
-    if (boostedTextFastPath.returnFastPath) {
+    if (!args.forceEmbedding && boostedTextFastPath.returnFastPath) {
       markEmbeddingSkippedByTextFastPath(telemetry, boostedTextFastPath.reason);
       telemetry.retrieval_strategy = "text_fast_path";
       recordSearchScoreTelemetry(telemetry, textFastResults);
@@ -5673,7 +5678,7 @@ export async function searchChunksWithTelemetry(args: SearchChunksArgs) {
         documentLookupResults,
         queryClassification.queryClass,
       );
-      if (documentLookupFastPath.returnFastPath) {
+      if (!args.forceEmbedding && documentLookupFastPath.returnFastPath) {
         markEmbeddingSkippedByTextFastPath(
           telemetry,
           documentLookupFastPath.reason ? `document_lookup_fast_path:${documentLookupFastPath.reason}` : null,
@@ -5700,7 +5705,7 @@ export async function searchChunksWithTelemetry(args: SearchChunksArgs) {
     });
     const coverageGate = evaluateEvidenceCoverageGate(args.query, coverageGateResults, queryClassification.queryClass);
     applyCoverageGateTelemetry(telemetry, coverageGate, coverageGate.accepted);
-    if (coverageGate.accepted) {
+    if (!args.forceEmbedding && coverageGate.accepted) {
       telemetry.retrieval_strategy = coverageGate.strategy;
       recordSearchScoreTelemetry(telemetry, coverageGateResults);
       setCachedSearch(args, coverageGateResults, telemetry, queryVariants);
@@ -5744,6 +5749,13 @@ export async function searchChunksWithTelemetry(args: SearchChunksArgs) {
     latencyMs: telemetry.embedding_latency_ms,
   });
 
+  if (args.forceEmbedding) {
+    // Force-embedding eval isolation: drop the lexical / memory-card / table candidates gathered
+    // before embedding so the returned results reflect the embedding-driven retrieval layers only
+    // (otherwise a broken vector index could still be masked by the lexical text candidate path).
+    textFastResults = [];
+  }
+
   // A1: the embedding-field, index-unit, and chunk-hybrid RPCs each depend only on the
   // already-computed query embedding and have no data dependency on one another, so run
   // them concurrently instead of as three sequential Supabase round-trips. The two helper
@@ -5780,7 +5792,7 @@ export async function searchChunksWithTelemetry(args: SearchChunksArgs) {
       const startedAt = Date.now();
       const { data, error } = await supabase.rpc("match_document_chunks_hybrid", {
         query_embedding: embedding as unknown as string,
-        query_text: textSearchQuery,
+        query_text: args.forceEmbedding ? "" : textSearchQuery,
         match_count: candidateCount,
         min_similarity: minSimilarity,
         document_filters: documentFilterList ?? undefined,