v1.11.6: doom-loop guard (3 identical tool calls aborts recursion)

apps/server/src/services/__tests__/doom-loop.test.ts

@@ -0,0 +1,130 @@
+import { describe, it, expect } from 'vitest';
+import { DOOM_LOOP_THRESHOLD, detectDoomLoop } from '../inference.js';
+import type { ToolCall } from '../../types/api.js';
+
+// ---- fixture ----------------------------------------------------------------
+// Tiny helper. `id` is required on ToolCall but irrelevant to detection —
+// detectDoomLoop compares name + JSON.stringify(args). Counter-based id keeps
+// each call unique so we don't accidentally test id-based equality.
+
+let counter = 0;
+function mkCall(name: string, args: Record<string, unknown> = {}): ToolCall {
+  counter += 1;
+  return { id: `c${counter}`, name, args };
+}
+
+// ---- below-threshold -------------------------------------------------------
+
+describe('detectDoomLoop — below threshold', () => {
+  it('returns null for an empty array', () => {
+    expect(detectDoomLoop([])).toBeNull();
+  });
+
+  it('returns null when fewer than DOOM_LOOP_THRESHOLD calls exist', () => {
+    // 2 < 3 — sliding-window can't form even if both match.
+    const a = mkCall('view_file', { path: 'a.ts' });
+    const b = mkCall('view_file', { path: 'a.ts' });
+    expect(detectDoomLoop([a, b])).toBeNull();
+  });
+});
+
+// ---- positive detection ----------------------------------------------------
+
+describe('detectDoomLoop — positive matches', () => {
+  it('returns name + args when exactly DOOM_LOOP_THRESHOLD identical calls land', () => {
+    const calls = [
+      mkCall('grep', { pattern: 'TODO', path: 'src' }),
+      mkCall('grep', { pattern: 'TODO', path: 'src' }),
+      mkCall('grep', { pattern: 'TODO', path: 'src' }),
+    ];
+    const result = detectDoomLoop(calls);
+    expect(result).not.toBeNull();
+    expect(result!.name).toBe('grep');
+    expect(result!.args).toEqual({ pattern: 'TODO', path: 'src' });
+  });
+
+  it('matches sliding window — last DOOM_LOOP_THRESHOLD match even with earlier non-matching calls', () => {
+    // 4 calls: first differs, last 3 are identical → fire.
+    const calls = [
+      mkCall('list_dir', { path: '/' }),
+      mkCall('view_file', { path: 'a.ts' }),
+      mkCall('view_file', { path: 'a.ts' }),
+      mkCall('view_file', { path: 'a.ts' }),
+    ];
+    const result = detectDoomLoop(calls);
+    expect(result).not.toBeNull();
+    expect(result!.name).toBe('view_file');
+  });
+
+  it('matches identical empty-args calls (defense against {} !== {} reference bug)', () => {
+    // JSON.stringify on two distinct {} both produce '{}'. Confirms the
+    // detector uses value-equality not reference-equality.
+    const calls = [mkCall('ping', {}), mkCall('ping', {}), mkCall('ping', {})];
+    expect(detectDoomLoop(calls)).not.toBeNull();
+  });
+
+  it('matches calls with nested args of equal shape', () => {
+    // Deep-equal via JSON.stringify. If the model emits the same nested
+    // object three times, that's still a loop.
+    const nested = { filter: { glob: '*.ts', case: 'sensitive' }, limit: 50 };
+    const calls = [
+      mkCall('find_files', { ...nested }),
+      mkCall('find_files', { ...nested }),
+      mkCall('find_files', { ...nested }),
+    ];
+    expect(detectDoomLoop(calls)).not.toBeNull();
+  });
+});
+
+// ---- negative detection ----------------------------------------------------
+
+describe('detectDoomLoop — negative cases', () => {
+  it('returns null when 3 calls share name but differ in args', () => {
+    const calls = [
+      mkCall('view_file', { path: 'a.ts' }),
+      mkCall('view_file', { path: 'b.ts' }),
+      mkCall('view_file', { path: 'c.ts' }),
+    ];
+    expect(detectDoomLoop(calls)).toBeNull();
+  });
+
+  it('returns null when 3 calls share args but differ in name', () => {
+    const calls = [
+      mkCall('view_file', { path: 'a.ts' }),
+      mkCall('grep', { path: 'a.ts' }),
+      mkCall('list_dir', { path: 'a.ts' }),
+    ];
+    expect(detectDoomLoop(calls)).toBeNull();
+  });
+
+  it('returns null when the FIRST three of four match but the latest differs', () => {
+    // Critical sliding-window edge: detector must ONLY look at the last
+    // DOOM_LOOP_THRESHOLD entries. Earlier matches don't count if the
+    // model has since moved on.
+    const calls = [
+      mkCall('grep', { pattern: 'X' }),
+      mkCall('grep', { pattern: 'X' }),
+      mkCall('grep', { pattern: 'X' }),
+      mkCall('view_file', { path: 'a.ts' }),
+    ];
+    expect(detectDoomLoop(calls)).toBeNull();
+  });
+
+  it('returns null when args have same keys but different values', () => {
+    const calls = [
+      mkCall('grep', { pattern: 'TODO', path: 'src' }),
+      mkCall('grep', { pattern: 'TODO', path: 'src' }),
+      mkCall('grep', { pattern: 'TODO', path: 'apps' }),
+    ];
+    expect(detectDoomLoop(calls)).toBeNull();
+  });
+});
+
+// ---- threshold contract ----------------------------------------------------
+
+describe('DOOM_LOOP_THRESHOLD', () => {
+  it('is a positive integer (the public contract — tests assume 3)', () => {
+    expect(DOOM_LOOP_THRESHOLD).toBeGreaterThan(0);
+    expect(Number.isInteger(DOOM_LOOP_THRESHOLD)).toBe(true);
+  });
+});