Cap the hint prompt at 120 tokens: a full 223-token prompt garbles small models

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/hint-parity.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test";
 import { join } from "node:path";
-import { fitHintToBudget, normalizeHint } from "../src/lib/hint";
+import { fitHintToBudget, normalizeHint, PROMPT_TOKEN_BUDGET } from "../src/lib/hint";
 
 // D-WS2a: the server engine truncates the hint in Python (server-py/sidecar.py,
 // with faster-whisper's tokenizer) and the browser engine in TypeScript
@@ -34,11 +34,11 @@ sidecar = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(sidecar)
 encode = lambda text: [ord(c) for c in text]
 cases = json.load(sys.stdin)
-print(json.dumps([
+print(json.dumps({"budget": sidecar.PROMPT_TOKEN_BUDGET, "results": [
     {"normalized": sidecar.normalize_hint(c["hint"]),
      "ids": sidecar.fit_prompt_ids(c["hint"], encode, c["budget"])}
     for c in cases
-]))
+]}))
 `;
 
 describe("hint truncation parity: TypeScript vs sidecar.py", () => {
@@ -49,8 +49,12 @@ describe("hint truncation parity: TypeScript vs sidecar.py", () => {
       stderr: "pipe",
     });
     expect(proc.stderr.toString()).toBe("");
-    const python = JSON.parse(proc.stdout.toString()) as { normalized: string; ids: number[] }[];
-    expect(python).toEqual(
+    const python = JSON.parse(proc.stdout.toString()) as {
+      budget: number;
+      results: { normalized: string; ids: number[] }[];
+    };
+    expect(python.budget).toBe(PROMPT_TOKEN_BUDGET);
+    expect(python.results).toEqual(
       CASES.map(({ hint, budget }) => ({
         normalized: normalizeHint(hint),
         ids: fitHintToBudget(hint, charEncode, budget),

tests/hint.test.ts

@@ -96,13 +96,13 @@ describe("fitHintToBudget (D-WS2a truncation rule)", () => {
     expect(ids.length).toBe(10);
   });
 
-  test("a very long hint fits the 223-token budget and is a word prefix of the hint", () => {
+  test("a very long hint fits the 120-token budget and is a word prefix of the hint", () => {
     const words = Array.from({ length: 5000 }, (_, i) => `term${i}`);
     const hint = words.join(", ");
     const ids = fitHintToBudget(hint, charEncode);
-    expect(PROMPT_TOKEN_BUDGET).toBe(223);
-    expect(ids.length).toBeLessThanOrEqual(223);
-    expect(ids.length).toBeGreaterThan(200);
+    expect(PROMPT_TOKEN_BUDGET).toBe(120);
+    expect(ids.length).toBeLessThanOrEqual(120);
+    expect(ids.length).toBeGreaterThan(100);
     const kept = charDecode(ids);
     // Ends on a whole term plus the full stop: the hint continues with a separator there.
     expect(kept.endsWith(".")).toBe(true);

tests/prompt.test.ts

@@ -117,8 +117,8 @@ describe("buildPromptPrefix", () => {
     ]);
   });
 
-  test("a huge hint stays within the 223-token budget", () => {
+  test("a huge hint stays within the 120-token budget (D-WS2a)", () => {
     const prefix = buildPromptPrefix(tokenizer, "Maxwell, ".repeat(500));
-    expect(prefix.length).toBeLessThanOrEqual(224);
+    expect(prefix.length).toBeLessThanOrEqual(121);
   });
 });