diff --git a/src/lib/ai/coach/__tests__/labs-snapshot.test.ts b/src/lib/ai/coach/__tests__/labs-snapshot.test.ts
new file mode 100644
index 000000000..b3dfbd5dc
--- /dev/null
+++ b/src/lib/ai/coach/__tests__/labs-snapshot.test.ts
@@ -0,0 +1,171 @@
+import { describe, expect, it, vi, beforeEach } from "vitest";
+
+vi.mock("@/lib/db", () => ({
+  prisma: {
+    labResult: { findMany: vi.fn() },
+  },
+}));
+
+import { buildLabsSnapshotBlock, sanitizeValueText } from "../labs-snapshot";
+import { prisma } from "@/lib/db";
+
+const prismaMock = prisma as unknown as {
+  labResult: { findMany: ReturnType<typeof vi.fn> };
+};
+
+const NOW = new Date("2026-06-21T12:00:00.000Z");
+
+/** A linked numeric lab row (biomarker wins for name/unit/bounds). */
+function numericRow(overrides: Record<string, unknown> = {}) {
+  return {
+    analyte: "ldl-legacy",
+    panel: "legacy-panel",
+    value: 140,
+    valueText: null,
+    unit: "legacy-unit",
+    referenceLow: 50,
+    referenceHigh: 200,
+    takenAt: new Date("2026-06-01T08:00:00.000Z"),
+    biomarkerId: "bm_ldl",
+    biomarker: {
+      id: "bm_ldl",
+      name: "LDL",
+      unit: "mg/dL",
+      lowerBound: 0,
+      upperBound: 130,
+      panel: "Lipids",
+    },
+    ...overrides,
+  };
+}
+
+beforeEach(() => {
+  prismaMock.labResult.findMany.mockReset();
+});
+
+describe("buildLabsSnapshotBlock", () => {
+  it("returns null when the account has no readings", async () => {
+    prismaMock.labResult.findMany.mockResolvedValue([]);
+    const block = await buildLabsSnapshotBlock("user_1", NOW);
+    expect(block).toBeNull();
+  });
+
+  it("resolves name/unit/bounds from the linked biomarker and flags out-of-range", async () => {
+    prismaMock.labResult.findMany.mockResolvedValue([numericRow()]);
+    const block = await buildLabsSnapshotBlock("user_1", NOW);
+    expect(block).not.toBeNull();
+    expect(block!.recent).toHaveLength(1);
+    const r = block!.recent[0];
+    // Biomarker fields win over the stale per-row legacy columns.
+    expect(r.analyte).toBe("LDL");
+    expect(r.unit).toBe("mg/dL");
+    expect(r.referenceHigh).toBe(130);
+    expect(r.panel).toBe("Lipids");
+    // 140 > upperBound 130 → above.
+    expect(r.rangeStatus).toBe("above");
+    expect(r.value).toBe(140);
+    expect(r.valueText).toBeNull();
+  });
+
+  it("classifies an in-range numeric reading", async () => {
+    prismaMock.labResult.findMany.mockResolvedValue([
+      numericRow({ value: 100 }),
+    ]);
+    const block = await buildLabsSnapshotBlock("user_1", NOW);
+    expect(block!.recent[0].rangeStatus).toBe("in-range");
+  });
+
+  it("includes a qualitative reading with unknown range status", async () => {
+    prismaMock.labResult.findMany.mockResolvedValue([
+      {
+        analyte: "Hepatitis B",
+        panel: null,
+        value: null,
+        valueText: "negativ",
+        unit: "",
+        referenceLow: null,
+        referenceHigh: null,
+        takenAt: new Date("2026-05-10T08:00:00.000Z"),
+        biomarkerId: "bm_hep",
+        biomarker: {
+          id: "bm_hep",
+          name: "Hepatitis B",
+          unit: "",
+          lowerBound: null,
+          upperBound: null,
+          panel: null,
+        },
+      },
+    ]);
+    const block = await buildLabsSnapshotBlock("user_1", NOW);
+    const r = block!.recent[0];
+    expect(r.value).toBeNull();
+    expect(r.valueText).toBe("negativ");
+    expect(r.rangeStatus).toBe("unknown");
+  });
+
+  it("keeps only the most-recent reading per biomarker", async () => {
+    // findMany returns newest-first; the older duplicate must be dropped.
+    prismaMock.labResult.findMany.mockResolvedValue([
+      numericRow({ value: 120, takenAt: new Date("2026-06-10T08:00:00.000Z") }),
+      numericRow({ value: 145, takenAt: new Date("2026-01-10T08:00:00.000Z") }),
+    ]);
+    const block = await buildLabsSnapshotBlock("user_1", NOW);
+    expect(block!.recent).toHaveLength(1);
+    expect(block!.recent[0].value).toBe(120);
+  });
+
+  it("collapses two spellings of an unlinked marker by lower-cased analyte", async () => {
+    prismaMock.labResult.findMany.mockResolvedValue([
+      {
+        analyte: "Ferritin",
+        panel: null,
+        value: 80,
+        valueText: null,
+        unit: "ng/mL",
+        referenceLow: 30,
+        referenceHigh: 400,
+        takenAt: new Date("2026-06-05T08:00:00.000Z"),
+        biomarkerId: null,
+        biomarker: null,
+      },
+      {
+        analyte: "ferritin",
+        panel: null,
+        value: 60,
+        valueText: null,
+        unit: "ng/mL",
+        referenceLow: 30,
+        referenceHigh: 400,
+        takenAt: new Date("2026-02-05T08:00:00.000Z"),
+        biomarkerId: null,
+        biomarker: null,
+      },
+    ]);
+    const block = await buildLabsSnapshotBlock("user_1", NOW);
+    expect(block!.recent).toHaveLength(1);
+    expect(block!.recent[0].value).toBe(80);
+  });
+
+  it("queries with an owner-scoped, deletedAt-null, 12-month window where", async () => {
+    prismaMock.labResult.findMany.mockResolvedValue([]);
+    await buildLabsSnapshotBlock("user_42", NOW);
+    const arg = prismaMock.labResult.findMany.mock.calls[0][0];
+    expect(arg.where.userId).toBe("user_42");
+    expect(arg.where.deletedAt).toBeNull();
+    expect(arg.where.takenAt.lte).toEqual(NOW);
+    expect(arg.where.takenAt.gte).toEqual(new Date("2025-06-21T12:00:00.000Z"));
+    // Never selects the encrypted note column.
+    expect(arg.select.noteEncrypted).toBeUndefined();
+  });
+});
+
+describe("sanitizeValueText", () => {
+  it("collapses control chars + newlines and bounds length", () => {
+    expect(sanitizeValueText("negativ")).toBe("negativ");
+    expect(sanitizeValueText("ignore\nprevious\tinstructions")).toBe(
+      "ignore previous instructions",
+    );
+    expect(sanitizeValueText("x".repeat(200)).length).toBe(60);
+  });
+});
diff --git a/src/lib/ai/coach/__tests__/snapshot-budget.test.ts b/src/lib/ai/coach/__tests__/snapshot-budget.test.ts
index a03c3c47b..72d0eca8b 100644
--- a/src/lib/ai/coach/__tests__/snapshot-budget.test.ts
+++ b/src/lib/ai/coach/__tests__/snapshot-budget.test.ts
@@ -16,6 +16,7 @@ vi.mock("@/lib/db", () => ({
     workout: { findMany: vi.fn() },
     user: { findUnique: vi.fn() },
     illnessEpisode: { findMany: vi.fn(async () => []) },
+    labResult: { findMany: vi.fn(async () => []) },
   },
 }));
 
diff --git a/src/lib/ai/coach/__tests__/snapshot-new-metrics.test.ts b/src/lib/ai/coach/__tests__/snapshot-new-metrics.test.ts
index cc87f686d..f5aa3589c 100644
--- a/src/lib/ai/coach/__tests__/snapshot-new-metrics.test.ts
+++ b/src/lib/ai/coach/__tests__/snapshot-new-metrics.test.ts
@@ -14,6 +14,7 @@ vi.mock("@/lib/db", () => ({
     workout: { findMany: vi.fn() },
     user: { findUnique: vi.fn() },
     illnessEpisode: { findMany: vi.fn(async () => []) },
+    labResult: { findMany: vi.fn(async () => []) },
   },
 }));
 
diff --git a/src/lib/ai/coach/__tests__/snapshot.test.ts b/src/lib/ai/coach/__tests__/snapshot.test.ts
index 665e9da6e..fd36ba353 100644
--- a/src/lib/ai/coach/__tests__/snapshot.test.ts
+++ b/src/lib/ai/coach/__tests__/snapshot.test.ts
@@ -17,6 +17,8 @@ vi.mock("@/lib/db", () => ({
     user: { findUnique: vi.fn() },
     // v1.18.1 P4 — the illness context block reads active + recent episodes.
     illnessEpisode: { findMany: vi.fn(async () => []) },
+    // v1.18.11 (#65) — the labs context block reads recent lab results.
+    labResult: { findMany: vi.fn(async () => []) },
   },
 }));
 
diff --git a/src/lib/ai/coach/labs-snapshot.ts b/src/lib/ai/coach/labs-snapshot.ts
new file mode 100644
index 000000000..967bc1c50
--- /dev/null
+++ b/src/lib/ai/coach/labs-snapshot.ts
@@ -0,0 +1,177 @@
+/**
+ * v1.18.11 (#65) — lab-result context block for the Coach snapshot.
+ *
+ * Lets the Coach answer "what was my LDL last time" / "is my ferritin in
+ * range" from the user's own LabResult rows instead of guessing. The block is
+ * SERVER-AUTHORITATIVE and GROUNDED: each biomarker carries the canonical
+ * name, value, unit, resolved reference bounds, the in/out-of-range verdict,
+ * and the measured date — all computed from the DB via the same resolver the
+ * Labs API + doctor-report PDF use (`resolveLabFields` / `classifyReferenceRange`),
+ * never re-derived. The Coach reads these numbers verbatim and must not invent
+ * a lab value the block does not carry.
+ *
+ * Bounding (no unbounded history dump):
+ *  - MOST RECENT reading per biomarker only (one row per analyte).
+ *  - Last `LOOKBACK_MONTHS` months — stale panels do not enter the prompt.
+ *  - At most `MAX_BIOMARKERS` biomarkers, newest reading first, so a heavy
+ *    history can never balloon the prompt.
+ *
+ * Qualitative readings (`value` null, `valueText` "negativ" / …) are included
+ * with a neutral `"unknown"` range status — there is nothing to compare against
+ * the bounds, so no in/out verdict is fabricated. The free-text `valueText` is
+ * the one user-controlled string here, so it is sanitised (control chars +
+ * newlines collapsed, length bounded) before it can reach the prompt, mirroring
+ * the illness block's label handling. The encrypted `noteEncrypted` column is
+ * never selected — the decrypted note must not reach the prompt.
+ *
+ * `userId` is narrowed from the authenticated session by the caller and feeds
+ * the Prisma `where` field-by-field; it is never an input. Unlike the illness
+ * block, Labs is intentionally NOT module-gated (mirrors `/api/labs` — the data
+ * is always owner-scoped and safe to read), so the block is `null` only when the
+ * account has no recent readings.
+ */
+import { classifyReferenceRange } from "@/lib/labs/reference-range";
+import { resolveLabFields } from "@/lib/labs/serialise";
+import { prisma } from "@/lib/db";
+
+/** Only readings within this many months enter the prompt. */
+const LOOKBACK_MONTHS = 12;
+
+/** Cap on distinct biomarkers in the block (newest reading first). */
+const MAX_BIOMARKERS = 24;
+
+/** Max chars of the user-supplied qualitative `valueText` that may enter the prompt. */
+const MAX_VALUE_TEXT_CHARS = 60;
+
+/**
+ * Cap + strip the user-supplied qualitative result text before it enters the
+ * Coach LLM prompt. `valueText` is the one user-controlled string in this
+ * block, so it is a (self-scoped) prompt-injection surface: collapse control
+ * chars + newlines to spaces so an embedded "ignore previous instructions\n…"
+ * can't reshape the prompt structure, then bound the length. Mirrors
+ * `sanitizeLabel` in `illness-snapshot.ts`.
+ */
+export function sanitizeValueText(text: string): string {
+  let out = "";
+  for (const ch of text) {
+    const code = ch.codePointAt(0) ?? 0;
+    out += code < 0x20 || (code >= 0x7f && code <= 0x9f) ? " " : ch;
+  }
+  return out.replace(/\s+/g, " ").trim().slice(0, MAX_VALUE_TEXT_CHARS);
+}
+
+/** One biomarker's most-recent resolved reading. */
+export interface CoachLabReading {
+  /** Canonical analyte name (resolved from the linked biomarker when present). */
+  analyte: string;
+  /** Panel grouping, when the resolved marker carries one. */
+  panel: string | null;
+  /** Numeric reading; null for a qualitative row (see `valueText`). */
+  value: number | null;
+  /** Qualitative result text ("negativ" / …); null for a numeric row. */
+  valueText: string | null;
+  /** Resolved unit; empty for a qualitative marker. */
+  unit: string;
+  referenceLow: number | null;
+  referenceHigh: number | null;
+  /** in-range / below / above / unknown — computed from the resolved bounds. */
+  rangeStatus: "in-range" | "below" | "above" | "unknown";
+  /** Measured date (ISO). */
+  takenAt: string;
+}
+
+export interface CoachLabsBlock {
+  /** Most-recent reading per biomarker, newest first; bounded. */
+  recent: CoachLabReading[];
+}
+
+/**
+ * Build the labs context block, or `null` when the account has no readings in
+ * the lookback window. Selects label + value + resolved bounds + dates only —
+ * `noteEncrypted` is never selected.
+ */
+export async function buildLabsSnapshotBlock(
+  userId: string,
+  now: Date = new Date(),
+): Promise<CoachLabsBlock | null> {
+  const cutoff = new Date(now);
+  cutoff.setMonth(cutoff.getMonth() - LOOKBACK_MONTHS);
+
+  // Newest reading first; we keep only the first row seen per biomarker so the
+  // block carries the MOST RECENT value per analyte. Bounded fetch: at most a
+  // reading per capped biomarker plus headroom for older duplicates of the same
+  // marker. Field-by-field `where` — never a spread.
+  const rows = await prisma.labResult.findMany({
+    where: {
+      userId,
+      deletedAt: null,
+      takenAt: { gte: cutoff, lte: now },
+    },
+    orderBy: { takenAt: "desc" },
+    take: MAX_BIOMARKERS * 8,
+    select: {
+      analyte: true,
+      panel: true,
+      value: true,
+      valueText: true,
+      unit: true,
+      referenceLow: true,
+      referenceHigh: true,
+      takenAt: true,
+      biomarkerId: true,
+      biomarker: {
+        select: {
+          id: true,
+          name: true,
+          unit: true,
+          lowerBound: true,
+          upperBound: true,
+          panel: true,
+        },
+      },
+    },
+  });
+
+  if (rows.length === 0) return null;
+
+  // De-dup to the most-recent reading per biomarker. Key on the linked
+  // biomarker id when present (the canonical identity); fall back to the
+  // lower-cased resolved analyte for any legacy unlinked row so two spellings
+  // of the same marker still collapse. Rows arrive newest-first, so the first
+  // key sighting wins.
+  const seen = new Set<string>();
+  const recent: CoachLabReading[] = [];
+  for (const row of rows) {
+    const resolved = resolveLabFields(row, row.biomarker);
+    const key = row.biomarkerId ?? `analyte:${resolved.analyte.toLowerCase()}`;
+    if (seen.has(key)) continue;
+    seen.add(key);
+
+    recent.push({
+      analyte: resolved.analyte,
+      panel: resolved.panel,
+      value: row.value,
+      valueText: row.valueText ? sanitizeValueText(row.valueText) : null,
+      unit: resolved.unit,
+      referenceLow: resolved.referenceLow,
+      referenceHigh: resolved.referenceHigh,
+      // A qualitative row has nothing to compare against the bounds → neutral
+      // "unknown", never a fabricated verdict. A numeric row classifies.
+      rangeStatus:
+        row.value === null
+          ? "unknown"
+          : classifyReferenceRange(
+              row.value,
+              resolved.referenceLow,
+              resolved.referenceHigh,
+            ),
+      takenAt: row.takenAt.toISOString(),
+    });
+
+    if (recent.length >= MAX_BIOMARKERS) break;
+  }
+
+  if (recent.length === 0) return null;
+
+  return { recent };
+}
diff --git a/src/lib/ai/coach/snapshot.ts b/src/lib/ai/coach/snapshot.ts
index 1292ed9f7..60d5177ed 100644
--- a/src/lib/ai/coach/snapshot.ts
+++ b/src/lib/ai/coach/snapshot.ts
@@ -49,6 +49,7 @@ import { buildCoachMemoryBlock } from "./memory-snapshot";
 import { buildTrajectorySnapshotBlock } from "./trajectory-snapshot";
 import { buildCycleSnapshotBlock } from "./cycle-snapshot";
 import { buildIllnessSnapshotBlock } from "./illness-snapshot";
+import { buildLabsSnapshotBlock } from "./labs-snapshot";
 import {
   buildReferenceGroundingBlock,
   type GroundingMetricInput,
@@ -1255,6 +1256,14 @@ async function buildCoachSnapshotImpl(
   // degrader never sheds it — the Coach needs to know about Rest Mode.
   const illnessBlockPromise = buildIllnessSnapshotBlock(userId, now);
 
+  // v1.18.11 (#65) — lab-result context. Like illness it is CONTEXT, not a
+  // scope-gated metric: attached without a `registerBlock` so the budget
+  // degrader never sheds it, and Labs is intentionally not module-gated (the
+  // helper reads owner-scoped rows directly, mirroring `/api/labs`). The block
+  // carries the most-recent resolved reading per biomarker (last 12 months,
+  // capped) so the Coach can answer "what was my LDL" without re-deriving.
+  const labsBlockPromise = buildLabsSnapshotBlock(userId, now);
+
   const [
     moodRows,
     complianceMeds,
@@ -1269,6 +1278,7 @@ async function buildCoachSnapshotImpl(
     memoryBlock,
     cycleBlock,
     illnessBlock,
+    labsBlock,
   ] = await Promise.all([
     moodRowsPromise,
     complianceMedsPromise,
@@ -1283,6 +1293,7 @@ async function buildCoachSnapshotImpl(
     memoryBlockPromise,
     cycleBlockPromise,
     illnessBlockPromise,
+    labsBlockPromise,
   ]);
 
   const byType = (t: string) =>
@@ -2273,6 +2284,15 @@ async function buildCoachSnapshotImpl(
     snapshot.illness = illnessBlock;
   }
 
+  // v1.18.11 (#65) — lab-result context. Attached WITHOUT a cluster
+  // registration (like illness/scope): the budget degrader never sheds it, so
+  // the Coach can always answer a lab question from the user's own readings.
+  // Server-authoritative + grounded — resolved name/value/unit/range per
+  // biomarker, never the decrypted note.
+  if (labsBlock) {
+    snapshot.labs = labsBlock;
+  }
+
   if (Object.keys(snapshot).length === 0) {
     metrics.add("general");
   }
diff --git a/src/lib/ai/coach/system-prompt.ts b/src/lib/ai/coach/system-prompt.ts
index 35aad7aad..74b3590d3 100644
--- a/src/lib/ai/coach/system-prompt.ts
+++ b/src/lib/ai/coach/system-prompt.ts
@@ -313,6 +313,19 @@ ISO-week means.
   "recentResolved" is light history for "how often do I get sick"
   questions. When no "illness" block is present, assume nothing about
   the user's health status.
+- The SNAPSHOT MAY carry a "labs" block: { recent[] }, where each entry is
+  the user's MOST RECENT reading for one biomarker — { analyte, panel,
+  value, valueText, unit, referenceLow, referenceHigh, rangeStatus,
+  takenAt }. Numeric readings carry "value" + "unit"; qualitative ones
+  ("negativ" / …) carry "valueText" with "value" null. "rangeStatus" is
+  the server's verdict (in-range / below / above / unknown) against the
+  resolved reference bounds — read it as given, never recompute it.
+  Answer lab questions ONLY from this block: quote the value, unit, range,
+  and date verbatim, and never invent a lab number it does not carry. The
+  list is the latest value per marker over the last year, not a full
+  history. Frame results descriptively, never as a diagnosis. When no
+  "labs" block is present, you have no lab values — say so plainly rather
+  than guess.
 
 EVIDENCE BLOCK
 
@@ -687,6 +700,19 @@ ISO-Wochenmittel zusammen.
   Labels als die EIGENE beschreibende Angabe des Nutzers, nie als Diagnose;
   "recentResolved" ist leichte Historie für "wie oft bin ich krank".
   Fehlt der "illness"-Block, nimm nichts über den Gesundheitszustand an.
+- Der SNAPSHOT KANN einen "labs"-Block tragen: { recent[] }, wobei jeder
+  Eintrag der NEUESTE Wert des Nutzers für einen Biomarker ist — { analyte,
+  panel, value, valueText, unit, referenceLow, referenceHigh, rangeStatus,
+  takenAt }. Numerische Werte tragen "value" + "unit"; qualitative
+  ("negativ" / …) tragen "valueText" bei "value" null. "rangeStatus" ist das
+  serverseitige Urteil (in-range / below / above / unknown) gegen die
+  aufgelösten Referenzgrenzen — lies es wie angegeben, berechne es nie neu.
+  Beantworte Laborfragen NUR aus diesem Block: zitiere Wert, Einheit,
+  Bereich und Datum wörtlich und erfinde nie einen Laborwert, den der Block
+  nicht enthält. Die Liste ist der jeweils letzte Wert pro Marker aus dem
+  letzten Jahr, keine vollständige Historie. Formuliere Ergebnisse
+  beschreibend, nie als Diagnose. Fehlt der "labs"-Block, hast du keine
+  Laborwerte — sage das klar, statt zu raten.
 
 EVIDENZ-BLOCK