portal/tools/brain-retro-analyzer.test.mjs

import { describe, it, expect } from 'vitest';
import {
  dedupeEpisodes,
  inferOutcome,
  groupEpisodesToTasks,
  findCausalChains,
  buildFactorMatrix,
  analyze,
} from './brain-retro-analyzer.mjs';

// Minimal v2 episode for tests.
const ep = (overrides = {}) => ({
  schema_version: 2,
  task_id: 's1',
  task_ref: 's1',
  timestamps: { started_at: '2026-05-19T10:00:00Z', ended_at: '2026-05-19T10:05:00Z' },
  path_type: 'regulated',
  outcome: 'unknown',
  prompt_signal: 'neutral',
  decision_provenance: { kind: 'autonomous', claude_would_have_chosen: null },
  environment: { economy_level: 0, model: 'claude-opus-4-7', post_compaction: false, session_turn: 1, parallel_session: false },
  task_size: { tool_calls: 5, files_touched: 1, files: ['/a.js'] },
  primary_rationale: { step: 1, node_chosen: 'direct', triggers_matched: [], candidates_considered: [], boundaries_applied: [], hard_floor: { invoked: false, rules: [] }, task_classification: 'feature' },
  events: [],
  ...overrides,
});

describe('dedupeEpisodes', () => {
  it('keeps the last of two episodes with the same task_id + started_at', () => {
    const a = ep({ outcome: 'unknown' });
    const b = ep({ outcome: 'partial' }); // same task_id + started_at — routing-gate double-write
    const out = dedupeEpisodes([a, b]);
    expect(out).toHaveLength(1);
    expect(out[0].outcome).toBe('partial');
  });

  it('keeps all observer_error markers', () => {
    const out = dedupeEpisodes([ep(), { observer_error: true, task_id: 'e' }, { observer_error: true, task_id: 'e2' }]);
    expect(out.filter((e) => e.observer_error)).toHaveLength(2);
  });
});

describe('inferOutcome', () => {
  it('infers rework when the next episode opens with a correction', () => {
    expect(inferOutcome(ep(), ep({ prompt_signal: 'correction' }))).toBe('rework');
  });
  it('infers success when the next episode opens with approval', () => {
    expect(inferOutcome(ep(), ep({ prompt_signal: 'approval' }))).toBe('success');
  });
  it('infers partial when the episode has an interrupt event', () => {
    expect(inferOutcome(ep({ events: [{ kind: 'interrupt' }] }), ep())).toBe('partial');
  });
  it('infers unknown when there is no next episode', () => {
    expect(inferOutcome(ep(), null)).toBe('unknown');
  });
  it('infers blocked when the episode has more error than retry events', () => {
    const blocked = ep({ events: [{ kind: 'error' }, { kind: 'error' }, { kind: 'retry' }] });
    expect(inferOutcome(blocked, ep({ prompt_signal: 'approval' }))).toBe('blocked');
  });
  it('does not infer blocked when every error was retried', () => {
    const recovered = ep({ events: [{ kind: 'error' }, { kind: 'retry' }] });
    expect(inferOutcome(recovered, ep({ prompt_signal: 'approval' }))).toBe('success');
  });
});

describe('groupEpisodesToTasks', () => {
  it('starts a new task after a success and on a new_task prompt', () => {
    const eps = [
      ep({ timestamps: { started_at: '2026-05-19T10:00:00Z', ended_at: '2026-05-19T10:01:00Z' }, prompt_signal: 'new_task' }),
      ep({ timestamps: { started_at: '2026-05-19T10:02:00Z', ended_at: '2026-05-19T10:03:00Z' }, prompt_signal: 'approval' }),
      ep({ timestamps: { started_at: '2026-05-19T10:04:00Z', ended_at: '2026-05-19T10:05:00Z' }, prompt_signal: 'new_task' }),
    ];
    const tasks = groupEpisodesToTasks(eps);
    expect(tasks.length).toBeGreaterThanOrEqual(2);
  });
});

describe('findCausalChains', () => {
  it('links an errored episode to a later episode that shares a file', () => {
    const a = ep({ timestamps: { started_at: '2026-05-19T10:00:00Z', ended_at: '2026-05-19T10:01:00Z' }, events: [{ kind: 'error', message: 'x' }], task_size: { tool_calls: 1, files_touched: 1, files: ['/shared.js'] } });
    const b = ep({ timestamps: { started_at: '2026-05-19T10:02:00Z', ended_at: '2026-05-19T10:03:00Z' }, task_size: { tool_calls: 1, files_touched: 1, files: ['/shared.js'] } });
    const chains = findCausalChains([a, b]);
    expect(chains).toHaveLength(1);
    expect(chains[0].sharedFiles).toEqual(['/shared.js']);
  });

  it('returns no chain when no files are shared', () => {
    const a = ep({ events: [{ kind: 'error', message: 'x' }], task_size: { tool_calls: 1, files_touched: 1, files: ['/a.js'] } });
    const b = ep({ timestamps: { started_at: '2026-05-19T10:02:00Z', ended_at: '2026-05-19T10:03:00Z' }, task_size: { tool_calls: 1, files_touched: 1, files: ['/b.js'] } });
    expect(findCausalChains([a, b])).toHaveLength(0);
  });
});

describe('buildFactorMatrix', () => {
  it('tabulates outcome distribution per factor value', () => {
    const eps = [
      { ...ep(), _inferredOutcome: 'rework', decision_provenance: { kind: 'user_directed_method' } },
      { ...ep(), _inferredOutcome: 'success', decision_provenance: { kind: 'autonomous' } },
    ];
    const m = buildFactorMatrix(eps);
    expect(m.decision_provenance.user_directed_method.rework).toBe(1);
    expect(m.decision_provenance.autonomous.success).toBe(1);
  });

  it('counts the 3rd kind user_chose_from_options on the provenance axis', () => {
    const eps = [
      { ...ep(), _inferredOutcome: 'success', decision_provenance: { kind: 'autonomous' } },
      { ...ep(), _inferredOutcome: 'rework', decision_provenance: { kind: 'user_directed_method' } },
      { ...ep(), _inferredOutcome: 'success', decision_provenance: { kind: 'user_chose_from_options' } },
      { ...ep(), _inferredOutcome: 'rework', decision_provenance: { kind: 'user_chose_from_options' } },
    ];
    const m = buildFactorMatrix(eps);
    expect(m.decision_provenance).toHaveProperty('autonomous');
    expect(m.decision_provenance).toHaveProperty('user_directed_method');
    expect(m.decision_provenance).toHaveProperty('user_chose_from_options');
    expect(m.decision_provenance.user_chose_from_options.success).toBe(1);
    expect(m.decision_provenance.user_chose_from_options.rework).toBe(1);
  });

  it('includes session_turn (bucketed) and parallel_session factors', () => {
    const eps = [
      { ...ep(), _inferredOutcome: 'success', environment: { session_turn: 3, parallel_session: false } },
      { ...ep(), _inferredOutcome: 'rework', environment: { session_turn: 120, parallel_session: true } },
    ];
    const m = buildFactorMatrix(eps);
    expect(m.session_turn.early.success).toBe(1);
    expect(m.session_turn.late.rework).toBe(1);
    expect(m.parallel_session.false.success).toBe(1);
    expect(m.parallel_session.true.rework).toBe(1);
  });
});

describe('analyze', () => {
  it('returns episodeCount, tasks, causalChains and factorMatrix', () => {
    const result = analyze([ep(), ep({ timestamps: { started_at: '2026-05-19T11:00:00Z', ended_at: '2026-05-19T11:01:00Z' }, prompt_signal: 'correction' })]);
    expect(result.episodeCount).toBe(2);
    expect(result.factorMatrix).toBeDefined();
    expect(Array.isArray(result.tasks)).toBe(true);
    expect(Array.isArray(result.causalChains)).toBe(true);
  });

  it('skips v1 episodes (no schema_version 2) from the analysis', () => {
    const v1 = { task_id: 's-old', timestamps: { started_at: '2026-05-19T09:00:00Z' }, outcome: 'success' };
    const result = analyze([
      v1,
      ep(),
      ep({ timestamps: { started_at: '2026-05-19T11:00:00Z', ended_at: '2026-05-19T11:01:00Z' } }),
    ]);
    expect(result.episodeCount).toBe(2);
    expect(result.v1SkippedCount).toBe(1);
  });
});