portal/tools/enforce-classifier-match.test.mjs

import { describe, it, expect } from 'vitest';
import { decide } from './enforce-classifier-match.mjs';

describe('enforce-classifier-match / decide', () => {
  it('allows pure conversation (no mutating tools)', () => {
    expect(decide({
      toolUses: [{ name: 'Read' }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.9,
    }).block).toBe(false);
  });

  it('allows when no recommendation', () => {
    expect(decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: null,
      confidence: null,
    }).block).toBe(false);
  });

  it('allows when confidence below threshold', () => {
    expect(decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.5,
    }).block).toBe(false);
  });

  // Raised 2026-05-27 (retro #8 follow-up): borderline 0.7 confidence was the
  // source of false-positive blocks (#3 GitHub MCP for local debug, #36
  // adr-kit for status readouts). Threshold raised 0.7 → 0.8 so 0.7 and 0.75
  // no longer block.
  it('allows when confidence exactly 0.7 (raised threshold)', () => {
    expect(decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.7,
    }).block).toBe(false);
  });

  it('allows when confidence 0.75 (still under raised threshold)', () => {
    expect(decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.75,
    }).block).toBe(false);
  });

  it('blocks when recommendation high-confidence + no matching tool', () => {
    const r = decide({
      toolUses: [{ name: 'Edit', input: { file_path: 'x.mjs' } }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.9,
    });
    expect(r.block).toBe(true);
    expect(r.message).toMatch(/writing-plans/);
  });

  it('allows when Skill tool invoked with matching name', () => {
    const r = decide({
      toolUses: [
        { name: 'Skill', input: { skill: 'superpowers:writing-plans' } },
        { name: 'Edit', input: { file_path: 'x.mjs' } },
      ],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.9,
    });
    expect(r.block).toBe(false);
  });

  it('matches normalized name without superpowers: prefix', () => {
    const r = decide({
      toolUses: [
        { name: 'Skill', input: { skill: 'writing-plans' } },
        { name: 'Edit', input: {} },
      ],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.9,
    });
    expect(r.block).toBe(false);
  });

  it('matches Task subagent', () => {
    const r = decide({
      toolUses: [
        { name: 'Task', input: { subagent_type: 'rls-reviewer' } },
        { name: 'Edit', input: {} },
      ],
      recommendation: 'rls-reviewer',
      confidence: 0.85,
    });
    expect(r.block).toBe(false);
  });

  it('blocks (not allows) when only "override:" in assistant text — self-override removed (hole 1)', () => {
    const r = decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'foo:bar',
      confidence: 0.9,
      assistantText: 'override: simpler direct edit, foo:bar overkill here\n',
      override: null,
    });
    expect(r.block).toBe(true);
  });

  it('blocks when assistant text has "override: reason" but user prompt has no override phrase (hole 1)', () => {
    const r = decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.9,
      assistantText: 'override: just doing it quick',
      override: null,
    });
    expect(r.block).toBe(true);
  });

  it('allows when override phrase present', () => {
    const r = decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'foo:bar',
      confidence: 0.9,
      override: { phrase: 'direct ok', suppresses: ['classifier-mismatch'] },
    });
    expect(r.block).toBe(false);
  });

  it('blocks when Task subagent is spawned without matching recommendation (hole 2)', () => {
    const r = decide({
      toolUses: [{ name: 'Task', input: { subagent_type: 'general-purpose', prompt: 'do stuff' } }],
      recommendation: 'superpowers:writing-plans',
      confidence: 0.9,
      assistantText: '',
      override: null,
    });
    expect(r.block).toBe(true);
  });

  it('does NOT block when Task subagent matches recommendation (regression — Task should count as match when right type)', () => {
    const r = decide({
      toolUses: [{ name: 'Task', input: { subagent_type: 'writing-plans', prompt: '...' } }],
      recommendation: 'writing-plans',
      confidence: 0.9,
      assistantText: '',
      override: null,
    });
    expect(r.block).toBe(false);
  });

  it('does not match meta-planning to planning recommendation (hole 5)', () => {
    const r = decide({
      toolUses: [{ name: 'Skill', input: { skill: 'meta-planning' } }, { name: 'Edit', input: {} }],
      recommendation: 'planning',
      confidence: 0.9,
      assistantText: '',
      override: null,
    });
    expect(r.block).toBe(true);
  });

  it('matches superpowers:writing-plans to writing-plans recommendation (regression — keep working)', () => {
    expect(decide({
      toolUses: [{ name: 'Skill', input: { skill: 'superpowers:writing-plans' } }, { name: 'Edit', input: {} }],
      recommendation: 'writing-plans',
      confidence: 0.9,
      assistantText: '',
      override: null,
    }).block).toBe(false);
  });

  it('matches exact-name skill regression — keep working', () => {
    expect(decide({
      toolUses: [{ name: 'Skill', input: { skill: 'brainstorming' } }, { name: 'Edit', input: {} }],
      recommendation: 'brainstorming',
      confidence: 0.9,
      assistantText: '',
      override: null,
    }).block).toBe(false);
  });

  // hole 4: triggers_matched fallback — decide() contract test
  it('blocks when recommendation comes from triggers_matched fallback (hole 4, null confidence)', () => {
    const r = decide({
      toolUses: [{ name: 'Edit', input: {} }],
      recommendation: 'superpowers:writing-plans',  // would-be from triggers_matched[0]
      confidence: null,                              // no LLM, but triggers present
      assistantText: '',
      override: null,
    });
    expect(r.block).toBe(true);
  });
});