~cytrogen/gstack

ref: 3e3843c4a9c1cc01bcecab486818705ab7553e2b gstack/test/skill-e2e.test.ts -rw-r--r-- 52.8 KiB
3e3843c4 — Garry Tan feat: contributor mode, session awareness, recommendation format (#90) a month ago
                                                                                
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { runSkillTest } from './helpers/session-runner';
import type { SkillTestResult } from './helpers/session-runner';
import { outcomeJudge } from './helpers/llm-judge';
import { EvalCollector, judgePassed } from './helpers/eval-store';
import type { EvalTestEntry } from './helpers/eval-store';
import { startTestServer } from '../browse/test/test-server';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';

const ROOT = path.resolve(import.meta.dir, '..');

// Skip unless EVALS=1. Session runner strips CLAUDE* env vars to avoid nested session issues.
const evalsEnabled = !!process.env.EVALS;
const describeE2E = evalsEnabled ? describe : describe.skip;

// Eval result collector — accumulates test results, writes to ~/.gstack-dev/evals/ on finalize
const evalCollector = evalsEnabled ? new EvalCollector('e2e') : null;

// Unique run ID for this E2E session — used for heartbeat + per-run log directory
const runId = new Date().toISOString().replace(/[:.]/g, '').replace('T', '-').slice(0, 15);

/** DRY helper to record an E2E test result into the eval collector. */
function recordE2E(name: string, suite: string, result: SkillTestResult, extra?: Partial<EvalTestEntry>) {
  // Derive last tool call from transcript for machine-readable diagnostics
  const lastTool = result.toolCalls.length > 0
    ? `${result.toolCalls[result.toolCalls.length - 1].tool}(${JSON.stringify(result.toolCalls[result.toolCalls.length - 1].input).slice(0, 60)})`
    : undefined;

  evalCollector?.addTest({
    name, suite, tier: 'e2e',
    passed: result.exitReason === 'success' && result.browseErrors.length === 0,
    duration_ms: result.duration,
    cost_usd: result.costEstimate.estimatedCost,
    transcript: result.transcript,
    output: result.output?.slice(0, 2000),
    turns_used: result.costEstimate.turnsUsed,
    browse_errors: result.browseErrors,
    exit_reason: result.exitReason,
    timeout_at_turn: result.exitReason === 'timeout' ? result.costEstimate.turnsUsed : undefined,
    last_tool_call: lastTool,
    ...extra,
  });
}

let testServer: ReturnType<typeof startTestServer>;
let tmpDir: string;
const browseBin = path.resolve(ROOT, 'browse', 'dist', 'browse');

/**
 * Copy a directory tree recursively (files only, follows structure).
 */
function copyDirSync(src: string, dest: string) {
  fs.mkdirSync(dest, { recursive: true });
  for (const entry of fs.readdirSync(src, { withFileTypes: true })) {
    const srcPath = path.join(src, entry.name);
    const destPath = path.join(dest, entry.name);
    if (entry.isDirectory()) {
      copyDirSync(srcPath, destPath);
    } else {
      fs.copyFileSync(srcPath, destPath);
    }
  }
}

/**
 * Set up browse shims (binary symlink, find-browse, remote-slug) in a tmpDir.
 */
function setupBrowseShims(dir: string) {
  // Symlink browse binary
  const binDir = path.join(dir, 'browse', 'dist');
  fs.mkdirSync(binDir, { recursive: true });
  if (fs.existsSync(browseBin)) {
    fs.symlinkSync(browseBin, path.join(binDir, 'browse'));
  }

  // find-browse shim
  const findBrowseDir = path.join(dir, 'browse', 'bin');
  fs.mkdirSync(findBrowseDir, { recursive: true });
  fs.writeFileSync(
    path.join(findBrowseDir, 'find-browse'),
    `#!/bin/bash\necho "${browseBin}"\n`,
    { mode: 0o755 },
  );

  // remote-slug shim (returns test-project)
  fs.writeFileSync(
    path.join(findBrowseDir, 'remote-slug'),
    `#!/bin/bash\necho "test-project"\n`,
    { mode: 0o755 },
  );
}

/**
 * Print cost summary after an E2E test.
 */
function logCost(label: string, result: { costEstimate: { turnsUsed: number; estimatedTokens: number; estimatedCost: number }; duration: number }) {
  const { turnsUsed, estimatedTokens, estimatedCost } = result.costEstimate;
  const durationSec = Math.round(result.duration / 1000);
  console.log(`${label}: $${estimatedCost.toFixed(2)} (${turnsUsed} turns, ${(estimatedTokens / 1000).toFixed(1)}k tokens, ${durationSec}s)`);
}

/**
 * Dump diagnostic info on planted-bug outcome failure (decision 1C).
 */
function dumpOutcomeDiagnostic(dir: string, label: string, report: string, judgeResult: any) {
  try {
    const transcriptDir = path.join(dir, '.gstack', 'test-transcripts');
    fs.mkdirSync(transcriptDir, { recursive: true });
    const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
    fs.writeFileSync(
      path.join(transcriptDir, `${label}-outcome-${timestamp}.json`),
      JSON.stringify({ label, report, judgeResult }, null, 2),
    );
  } catch { /* non-fatal */ }
}

// Fail fast if Anthropic API is unreachable — don't burn through 13 tests getting ConnectionRefused
if (evalsEnabled) {
  const check = spawnSync('sh', ['-c', 'echo "ping" | claude -p --max-turns 1 --output-format stream-json --verbose --dangerously-skip-permissions'], {
    stdio: 'pipe', timeout: 30_000,
  });
  const output = check.stdout?.toString() || '';
  if (output.includes('ConnectionRefused') || output.includes('Unable to connect')) {
    throw new Error('Anthropic API unreachable — aborting E2E suite. Fix connectivity and retry.');
  }
}

describeE2E('Skill E2E tests', () => {
  beforeAll(() => {
    testServer = startTestServer();
    tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-'));
    setupBrowseShims(tmpDir);
  });

  afterAll(() => {
    testServer?.server?.stop();
    try { fs.rmSync(tmpDir, { recursive: true, force: true }); } catch {}
  });

  test('browse basic commands work without errors', async () => {
    const result = await runSkillTest({
      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run these commands in sequence:
1. $B goto ${testServer.url}
2. $B snapshot -i
3. $B text
4. $B screenshot /tmp/skill-e2e-test.png
Report the results of each command.`,
      workingDirectory: tmpDir,
      maxTurns: 10,
      timeout: 60_000,
      testName: 'browse-basic',
      runId,
    });

    logCost('browse basic', result);
    recordE2E('browse basic commands', 'Skill E2E tests', result);
    expect(result.browseErrors).toHaveLength(0);
    expect(result.exitReason).toBe('success');
  }, 90_000);

  test('browse snapshot flags all work', async () => {
    const result = await runSkillTest({
      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run:
1. $B goto ${testServer.url}
2. $B snapshot -i
3. $B snapshot -c
4. $B snapshot -D
5. $B snapshot -i -a -o /tmp/skill-e2e-annotated.png
Report what each command returned.`,
      workingDirectory: tmpDir,
      maxTurns: 10,
      timeout: 60_000,
      testName: 'browse-snapshot',
      runId,
    });

    logCost('browse snapshot', result);
    recordE2E('browse snapshot flags', 'Skill E2E tests', result);
    // browseErrors can include false positives from hallucinated paths (e.g. "baltimore" vs "bangalore")
    if (result.browseErrors.length > 0) {
      console.warn('Browse errors (non-fatal):', result.browseErrors);
    }
    expect(result.exitReason).toBe('success');
  }, 90_000);

  test('agent discovers browse binary via SKILL.md setup block', async () => {
    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const setupStart = skillMd.indexOf('## SETUP');
    const setupEnd = skillMd.indexOf('## IMPORTANT');
    const setupBlock = skillMd.slice(setupStart, setupEnd);

    // Guard: verify we extracted a valid setup block
    expect(setupBlock).toContain('browse/dist/browse');

    const result = await runSkillTest({
      prompt: `Follow these instructions to find the browse binary and run a basic command.

${setupBlock}

After finding the binary, run: $B goto ${testServer.url}
Then run: $B text
Report whether it worked.`,
      workingDirectory: tmpDir,
      maxTurns: 10,
      timeout: 60_000,
      testName: 'skillmd-setup-discovery',
      runId,
    });

    recordE2E('SKILL.md setup block discovery', 'Skill E2E tests', result);
    expect(result.browseErrors).toHaveLength(0);
    expect(result.exitReason).toBe('success');
  }, 90_000);

  test('SKILL.md setup block handles missing local binary gracefully', async () => {
    // Create a tmpdir with no browse binary — no local .claude/skills/gstack/browse/dist/browse
    const emptyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-empty-'));

    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const setupStart = skillMd.indexOf('## SETUP');
    const setupEnd = skillMd.indexOf('## IMPORTANT');
    const setupBlock = skillMd.slice(setupStart, setupEnd);

    const result = await runSkillTest({
      prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.

${setupBlock}

Report the exact output. Do NOT try to fix or install anything — just report what you see.`,
      workingDirectory: emptyDir,
      maxTurns: 5,
      timeout: 30_000,
      testName: 'skillmd-no-local-binary',
      runId,
    });

    // Setup block should either find the global binary (READY) or show NEEDS_SETUP.
    // On dev machines with gstack installed globally, the fallback path
    // ~/.claude/skills/gstack/browse/dist/browse exists, so we get READY.
    // The important thing is it doesn't crash or give a confusing error.
    const allText = result.output || '';
    recordE2E('SKILL.md setup block (no local binary)', 'Skill E2E tests', result);
    expect(allText).toMatch(/READY|NEEDS_SETUP/);
    expect(result.exitReason).toBe('success');

    // Clean up
    try { fs.rmSync(emptyDir, { recursive: true, force: true }); } catch {}
  }, 60_000);

  test('SKILL.md setup block works outside git repo', async () => {
    // Create a tmpdir outside any git repo
    const nonGitDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-nogit-'));

    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const setupStart = skillMd.indexOf('## SETUP');
    const setupEnd = skillMd.indexOf('## IMPORTANT');
    const setupBlock = skillMd.slice(setupStart, setupEnd);

    const result = await runSkillTest({
      prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.

${setupBlock}

Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
      workingDirectory: nonGitDir,
      maxTurns: 5,
      timeout: 30_000,
      testName: 'skillmd-outside-git',
      runId,
    });

    // Should either find global binary (READY) or show NEEDS_SETUP — not crash
    const allText = result.output || '';
    recordE2E('SKILL.md outside git repo', 'Skill E2E tests', result);
    expect(allText).toMatch(/READY|NEEDS_SETUP/);

    // Clean up
    try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
  }, 60_000);

  test('contributor mode files a report on gstack error', async () => {
    const contribDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-contrib-'));
    const logsDir = path.join(contribDir, 'contributor-logs');
    fs.mkdirSync(logsDir, { recursive: true });

    // Extract contributor mode instructions from generated SKILL.md
    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const contribStart = skillMd.indexOf('## Contributor Mode');
    const contribEnd = skillMd.indexOf('\n## ', contribStart + 1);
    const contribBlock = skillMd.slice(contribStart, contribEnd > 0 ? contribEnd : undefined);

    const result = await runSkillTest({
      prompt: `You are in contributor mode (_CONTRIB=true).

${contribBlock}

OVERRIDE: Write contributor logs to ${logsDir}/ instead of ~/.gstack/contributor-logs/

Now try this browse command (it will fail — there is no binary at this path):
/nonexistent/path/browse goto https://example.com

This is a gstack issue (the browse binary is missing/misconfigured).
File a contributor report about this issue. Then tell me what you filed.`,
      workingDirectory: contribDir,
      maxTurns: 8,
      timeout: 60_000,
      testName: 'contributor-mode',
      runId,
    });

    logCost('contributor mode', result);
    // Override passed: this test intentionally triggers a browse error (nonexistent binary)
    // so browseErrors will be non-empty — that's expected, not a failure
    recordE2E('contributor mode report', 'Skill E2E tests', result, {
      passed: result.exitReason === 'success',
    });

    // Verify a contributor log was created with expected format
    const logFiles = fs.readdirSync(logsDir).filter(f => f.endsWith('.md'));
    expect(logFiles.length).toBeGreaterThan(0);

    const logContent = fs.readFileSync(path.join(logsDir, logFiles[0]), 'utf-8');
    expect(logContent).toContain('Hey gstack team');
    expect(logContent).toContain('What I was trying to do');
    expect(logContent).toContain('What happened instead');

    // Clean up
    try { fs.rmSync(contribDir, { recursive: true, force: true }); } catch {}
  }, 90_000);

  test('session awareness adds ELI16 context when _SESSIONS >= 3', async () => {
    const sessionDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-session-'));

    // Set up a git repo so there's project/branch context to reference
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: sessionDir, stdio: 'pipe', timeout: 5000 });
    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);
    fs.writeFileSync(path.join(sessionDir, 'app.rb'), '# my app\n');
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'init']);
    run('git', ['checkout', '-b', 'feature/add-payments']);
    // Add a remote so the agent can derive a project name
    run('git', ['remote', 'add', 'origin', 'https://github.com/acme/billing-app.git']);

    // Extract AskUserQuestion format instructions from generated SKILL.md
    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const aqStart = skillMd.indexOf('## AskUserQuestion Format');
    const aqEnd = skillMd.indexOf('\n## ', aqStart + 1);
    const aqBlock = skillMd.slice(aqStart, aqEnd > 0 ? aqEnd : undefined);

    const outputPath = path.join(sessionDir, 'question-output.md');

    const result = await runSkillTest({
      prompt: `You are running a gstack skill. The session preamble detected _SESSIONS=4 (the user has 4 gstack windows open).

${aqBlock}

You are on branch feature/add-payments in the billing-app project. You were reviewing a plan to add Stripe integration.

You've hit a decision point: the plan doesn't specify whether to use Stripe Checkout (hosted) or Stripe Elements (embedded). You need to ask the user which approach to use.

Since this is non-interactive, DO NOT actually call AskUserQuestion. Instead, write the EXACT text you would display to the user (the full AskUserQuestion content) to the file: ${outputPath}

Remember: _SESSIONS=4, so ELI16 mode is active. The user is juggling multiple windows and may not remember what this conversation is about. Re-ground them.`,
      workingDirectory: sessionDir,
      maxTurns: 8,
      timeout: 60_000,
      testName: 'session-awareness',
      runId,
    });

    logCost('session awareness', result);
    recordE2E('session awareness ELI16', 'Skill E2E tests', result);

    // Verify the output contains ELI16 re-grounding context
    if (fs.existsSync(outputPath)) {
      const output = fs.readFileSync(outputPath, 'utf-8');
      const lower = output.toLowerCase();
      // Must mention project name
      expect(lower.includes('billing') || lower.includes('acme')).toBe(true);
      // Must mention branch
      expect(lower.includes('payment') || lower.includes('feature')).toBe(true);
      // Must mention what we're working on
      expect(lower.includes('stripe') || lower.includes('checkout') || lower.includes('payment')).toBe(true);
      // Must have a RECOMMENDATION
      expect(output).toContain('RECOMMENDATION');
    } else {
      // Check agent output as fallback
      const output = result.output || '';
      expect(output).toContain('RECOMMENDATION');
    }

    // Clean up
    try { fs.rmSync(sessionDir, { recursive: true, force: true }); } catch {}
  }, 90_000);
});

// --- B4: QA skill E2E ---

describeE2E('QA skill E2E', () => {
  let qaDir: string;

  beforeAll(() => {
    testServer = testServer || startTestServer();
    qaDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-'));
    setupBrowseShims(qaDir);

    // Copy qa skill files into tmpDir
    copyDirSync(path.join(ROOT, 'qa'), path.join(qaDir, 'qa'));

    // Create report directory
    fs.mkdirSync(path.join(qaDir, 'qa-reports'), { recursive: true });
  });

  afterAll(() => {
    testServer?.server?.stop();
    try { fs.rmSync(qaDir, { recursive: true, force: true }); } catch {}
  });

  test('/qa quick completes without browse errors', async () => {
    const result = await runSkillTest({
      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable like: B="${browseBin}"

Read the file qa/SKILL.md for the QA workflow instructions.

Run a Quick-depth QA test on ${testServer.url}/basic.html
Do NOT use AskUserQuestion — run Quick tier directly.
Write your report to ${qaDir}/qa-reports/qa-report.md`,
      workingDirectory: qaDir,
      maxTurns: 35,
      timeout: 180_000,
      testName: 'qa-quick',
      runId,
    });

    logCost('/qa quick', result);
    recordE2E('/qa quick', 'QA skill E2E', result, {
      passed: ['success', 'error_max_turns'].includes(result.exitReason),
    });
    // browseErrors can include false positives from hallucinated paths
    if (result.browseErrors.length > 0) {
      console.warn('/qa quick browse errors (non-fatal):', result.browseErrors);
    }
    // Accept error_max_turns — the agent doing thorough QA work is not a failure
    expect(['success', 'error_max_turns']).toContain(result.exitReason);
  }, 240_000);
});

// --- B5: Review skill E2E ---

describeE2E('Review skill E2E', () => {
  let reviewDir: string;

  beforeAll(() => {
    reviewDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-review-'));

    // Pre-build a git repo with a vulnerable file on a feature branch (decision 5A)
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: reviewDir, stdio: 'pipe', timeout: 5000 });

    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);

    // Commit a clean base on main
    fs.writeFileSync(path.join(reviewDir, 'app.rb'), '# clean base\nclass App\nend\n');
    run('git', ['add', 'app.rb']);
    run('git', ['commit', '-m', 'initial commit']);

    // Create feature branch with vulnerable code
    run('git', ['checkout', '-b', 'feature/add-user-controller']);
    const vulnContent = fs.readFileSync(path.join(ROOT, 'test', 'fixtures', 'review-eval-vuln.rb'), 'utf-8');
    fs.writeFileSync(path.join(reviewDir, 'user_controller.rb'), vulnContent);
    run('git', ['add', 'user_controller.rb']);
    run('git', ['commit', '-m', 'add user controller']);

    // Copy review skill files
    fs.copyFileSync(path.join(ROOT, 'review', 'SKILL.md'), path.join(reviewDir, 'review-SKILL.md'));
    fs.copyFileSync(path.join(ROOT, 'review', 'checklist.md'), path.join(reviewDir, 'review-checklist.md'));
    fs.copyFileSync(path.join(ROOT, 'review', 'greptile-triage.md'), path.join(reviewDir, 'review-greptile-triage.md'));
  });

  afterAll(() => {
    try { fs.rmSync(reviewDir, { recursive: true, force: true }); } catch {}
  });

  test('/review produces findings on SQL injection branch', async () => {
    const result = await runSkillTest({
      prompt: `You are in a git repo on a feature branch with changes against main.
Read review-SKILL.md for the review workflow instructions.
Also read review-checklist.md and apply it.
Run /review on the current diff (git diff main...HEAD).
Write your review findings to ${reviewDir}/review-output.md`,
      workingDirectory: reviewDir,
      maxTurns: 15,
      timeout: 90_000,
      testName: 'review-sql-injection',
      runId,
    });

    logCost('/review', result);
    recordE2E('/review SQL injection', 'Review skill E2E', result);
    expect(result.exitReason).toBe('success');
  }, 120_000);
});

// --- Review: Enum completeness E2E ---

describeE2E('Review enum completeness E2E', () => {
  let enumDir: string;

  beforeAll(() => {
    enumDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-enum-'));

    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: enumDir, stdio: 'pipe', timeout: 5000 });

    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);

    // Commit baseline on main — order model with 4 statuses
    const baseContent = fs.readFileSync(path.join(ROOT, 'test', 'fixtures', 'review-eval-enum.rb'), 'utf-8');
    fs.writeFileSync(path.join(enumDir, 'order.rb'), baseContent);
    run('git', ['add', 'order.rb']);
    run('git', ['commit', '-m', 'initial order model']);

    // Feature branch adds "returned" status but misses handlers
    run('git', ['checkout', '-b', 'feature/add-returned-status']);
    const diffContent = fs.readFileSync(path.join(ROOT, 'test', 'fixtures', 'review-eval-enum-diff.rb'), 'utf-8');
    fs.writeFileSync(path.join(enumDir, 'order.rb'), diffContent);
    run('git', ['add', 'order.rb']);
    run('git', ['commit', '-m', 'add returned status']);

    // Copy review skill files
    fs.copyFileSync(path.join(ROOT, 'review', 'SKILL.md'), path.join(enumDir, 'review-SKILL.md'));
    fs.copyFileSync(path.join(ROOT, 'review', 'checklist.md'), path.join(enumDir, 'review-checklist.md'));
    fs.copyFileSync(path.join(ROOT, 'review', 'greptile-triage.md'), path.join(enumDir, 'review-greptile-triage.md'));
  });

  afterAll(() => {
    try { fs.rmSync(enumDir, { recursive: true, force: true }); } catch {}
  });

  test('/review catches missing enum handlers for new status value', async () => {
    const result = await runSkillTest({
      prompt: `You are in a git repo on branch feature/add-returned-status with changes against main.
Read review-SKILL.md for the review workflow instructions.
Also read review-checklist.md and apply it — pay special attention to the Enum & Value Completeness section.
Run /review on the current diff (git diff main...HEAD).
Write your review findings to ${enumDir}/review-output.md

The diff adds a new "returned" status to the Order model. Your job is to check if all consumers handle it.`,
      workingDirectory: enumDir,
      maxTurns: 15,
      timeout: 90_000,
      testName: 'review-enum-completeness',
      runId,
    });

    logCost('/review enum', result);
    recordE2E('/review enum completeness', 'Review enum completeness E2E', result);
    expect(result.exitReason).toBe('success');

    // Verify the review caught the missing enum handlers
    const reviewPath = path.join(enumDir, 'review-output.md');
    if (fs.existsSync(reviewPath)) {
      const review = fs.readFileSync(reviewPath, 'utf-8');
      // Should mention the missing "returned" handling in at least one of the methods
      const mentionsReturned = review.toLowerCase().includes('returned');
      const mentionsEnum = review.toLowerCase().includes('enum') || review.toLowerCase().includes('status');
      const mentionsCritical = review.toLowerCase().includes('critical');
      expect(mentionsReturned).toBe(true);
      expect(mentionsEnum || mentionsCritical).toBe(true);
    }
  }, 120_000);
});

// --- B6/B7/B8: Planted-bug outcome evals ---

// Outcome evals also need ANTHROPIC_API_KEY for the LLM judge
const hasApiKey = !!process.env.ANTHROPIC_API_KEY;
const describeOutcome = (evalsEnabled && hasApiKey) ? describe : describe.skip;

describeOutcome('Planted-bug outcome evals', () => {
  let outcomeDir: string;

  beforeAll(() => {
    // Always start fresh — previous tests' agents may have killed the shared server
    try { testServer?.server?.stop(); } catch {}
    testServer = startTestServer();
    outcomeDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-outcome-'));
    setupBrowseShims(outcomeDir);

    // Copy qa skill files
    copyDirSync(path.join(ROOT, 'qa'), path.join(outcomeDir, 'qa'));
  });

  afterAll(() => {
    testServer?.server?.stop();
    try { fs.rmSync(outcomeDir, { recursive: true, force: true }); } catch {}
  });

  /**
   * Shared planted-bug eval runner.
   * Gives the agent concise bug-finding instructions (not the full QA workflow),
   * then scores the report with an LLM outcome judge.
   */
  async function runPlantedBugEval(fixture: string, groundTruthFile: string, label: string) {
    // Each test gets its own isolated working directory to prevent cross-contamination
    // (agents reading previous tests' reports and hallucinating those bugs)
    const testWorkDir = fs.mkdtempSync(path.join(os.tmpdir(), `skill-e2e-${label}-`));
    setupBrowseShims(testWorkDir);
    const reportDir = path.join(testWorkDir, 'reports');
    fs.mkdirSync(path.join(reportDir, 'screenshots'), { recursive: true });
    const reportPath = path.join(reportDir, 'qa-report.md');

    // Direct bug-finding with browse. Keep prompt concise — no reading long SKILL.md docs.
    // "Write early, update later" pattern ensures report exists even if agent hits max turns.
    const targetUrl = `${testServer.url}/${fixture}`;
    const result = await runSkillTest({
      prompt: `Find bugs on this page: ${targetUrl}

Browser binary: B="${browseBin}"

PHASE 1 — Quick scan (5 commands max):
$B goto ${targetUrl}
$B console --errors
$B snapshot -i
$B snapshot -c
$B accessibility

PHASE 2 — Write initial report to ${reportPath}:
Write every bug you found so far. Format each as:
- Category: functional / visual / accessibility / console
- Severity: high / medium / low
- Evidence: what you observed

PHASE 3 — Interactive testing (targeted — max 15 commands):
- Test email: type "user@" (no domain) and blur — does it validate?
- Test quantity: clear the field entirely — check the total display
- Test credit card: type a 25-character string — check for overflow
- Submit the form with zip code empty — does it require zip?
- Submit a valid form and run $B console --errors
- After finding more bugs, UPDATE ${reportPath} with new findings

PHASE 4 — Finalize report:
- UPDATE ${reportPath} with ALL bugs found across all phases
- Include console errors, form validation issues, visual overflow, missing attributes

CRITICAL RULES:
- ONLY test the page at ${targetUrl} — do not navigate to other sites
- Write the report file in PHASE 2 before doing interactive testing
- The report MUST exist at ${reportPath} when you finish`,
      workingDirectory: testWorkDir,
      maxTurns: 50,
      timeout: 300_000,
      testName: `qa-${label}`,
      runId,
    });

    logCost(`/qa ${label}`, result);

    // Phase 1: browse mechanics. Accept error_max_turns — agent may have written
    // a partial report before running out of turns. What matters is detection rate.
    if (result.browseErrors.length > 0) {
      console.warn(`${label} browse errors:`, result.browseErrors);
    }
    if (result.exitReason !== 'success' && result.exitReason !== 'error_max_turns') {
      throw new Error(`${label}: unexpected exit reason: ${result.exitReason}`);
    }

    // Phase 2: Outcome evaluation via LLM judge
    const groundTruth = JSON.parse(
      fs.readFileSync(path.join(ROOT, 'test', 'fixtures', groundTruthFile), 'utf-8'),
    );

    // Read the generated report (try expected path, then glob for any .md in reportDir or workDir)
    let report: string | null = null;
    if (fs.existsSync(reportPath)) {
      report = fs.readFileSync(reportPath, 'utf-8');
    } else {
      // Agent may have named it differently — find any .md in reportDir or testWorkDir
      for (const searchDir of [reportDir, testWorkDir]) {
        try {
          const mdFiles = fs.readdirSync(searchDir).filter(f => f.endsWith('.md'));
          if (mdFiles.length > 0) {
            report = fs.readFileSync(path.join(searchDir, mdFiles[0]), 'utf-8');
            break;
          }
        } catch { /* dir may not exist if agent hit max_turns early */ }
      }

      // Also check the agent's final output for inline report content
      if (!report && result.output && result.output.length > 100) {
        report = result.output;
      }
    }

    if (!report) {
      dumpOutcomeDiagnostic(testWorkDir, label, '(no report file found)', { error: 'missing report' });
      recordE2E(`/qa ${label}`, 'Planted-bug outcome evals', result, { error: 'no report generated' });
      throw new Error(`No report file found in ${reportDir}`);
    }

    const judgeResult = await outcomeJudge(groundTruth, report);
    console.log(`${label} outcome:`, JSON.stringify(judgeResult, null, 2));

    // Record to eval collector with outcome judge results
    recordE2E(`/qa ${label}`, 'Planted-bug outcome evals', result, {
      passed: judgePassed(judgeResult, groundTruth),
      detection_rate: judgeResult.detection_rate,
      false_positives: judgeResult.false_positives,
      evidence_quality: judgeResult.evidence_quality,
      detected_bugs: judgeResult.detected,
      missed_bugs: judgeResult.missed,
    });

    // Diagnostic dump on failure (decision 1C)
    if (judgeResult.detection_rate < groundTruth.minimum_detection || judgeResult.false_positives > groundTruth.max_false_positives) {
      dumpOutcomeDiagnostic(testWorkDir, label, report, judgeResult);
    }

    // Phase 2 assertions
    expect(judgeResult.detection_rate).toBeGreaterThanOrEqual(groundTruth.minimum_detection);
    expect(judgeResult.false_positives).toBeLessThanOrEqual(groundTruth.max_false_positives);
    expect(judgeResult.evidence_quality).toBeGreaterThanOrEqual(2);
  }

  // B6: Static dashboard — broken link, disabled submit, overflow, missing alt, console error
  test('/qa finds >= 2 of 5 planted bugs (static)', async () => {
    await runPlantedBugEval('qa-eval.html', 'qa-eval-ground-truth.json', 'b6-static');
  }, 360_000);

  // B7: SPA — broken route, stale state, async race, missing aria, console warning
  test('/qa finds >= 2 of 5 planted SPA bugs', async () => {
    await runPlantedBugEval('qa-eval-spa.html', 'qa-eval-spa-ground-truth.json', 'b7-spa');
  }, 360_000);

  // B8: Checkout — email regex, NaN total, CC overflow, missing required, stripe error
  test('/qa finds >= 2 of 5 planted checkout bugs', async () => {
    await runPlantedBugEval('qa-eval-checkout.html', 'qa-eval-checkout-ground-truth.json', 'b8-checkout');
  }, 360_000);

});

// --- Plan CEO Review E2E ---

describeE2E('Plan CEO Review E2E', () => {
  let planDir: string;

  beforeAll(() => {
    planDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-plan-ceo-'));
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });

    // Init git repo (CEO review SKILL.md has a "System Audit" step that runs git)
    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);

    // Create a simple plan document for the agent to review
    fs.writeFileSync(path.join(planDir, 'plan.md'), `# Plan: Add User Dashboard

## Context
We're building a new user dashboard that shows recent activity, notifications, and quick actions.

## Changes
1. New React component \`UserDashboard\` in \`src/components/\`
2. REST API endpoint \`GET /api/dashboard\` returning user stats
3. PostgreSQL query for activity aggregation
4. Redis cache layer for dashboard data (5min TTL)

## Architecture
- Frontend: React + TailwindCSS
- Backend: Express.js REST API
- Database: PostgreSQL with existing user/activity tables
- Cache: Redis for dashboard aggregates

## Open questions
- Should we use WebSocket for real-time updates?
- How do we handle users with 100k+ activity records?
`);

    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'add plan']);

    // Copy plan-ceo-review skill
    fs.mkdirSync(path.join(planDir, 'plan-ceo-review'), { recursive: true });
    fs.copyFileSync(
      path.join(ROOT, 'plan-ceo-review', 'SKILL.md'),
      path.join(planDir, 'plan-ceo-review', 'SKILL.md'),
    );
  });

  afterAll(() => {
    try { fs.rmSync(planDir, { recursive: true, force: true }); } catch {}
  });

  test('/plan-ceo-review produces structured review output', async () => {
    const result = await runSkillTest({
      prompt: `Read plan-ceo-review/SKILL.md for the review workflow.

Read plan.md — that's the plan to review. This is a standalone plan document, not a codebase — skip any codebase exploration or system audit steps.

Choose HOLD SCOPE mode. Skip any AskUserQuestion calls — this is non-interactive.
Write your complete review directly to ${planDir}/review-output.md

Focus on reviewing the plan content: architecture, error handling, security, and performance.`,
      workingDirectory: planDir,
      maxTurns: 15,
      timeout: 360_000,
      testName: 'plan-ceo-review',
      runId,
    });

    logCost('/plan-ceo-review', result);
    recordE2E('/plan-ceo-review', 'Plan CEO Review E2E', result, {
      passed: ['success', 'error_max_turns'].includes(result.exitReason),
    });
    // Accept error_max_turns — the CEO review is very thorough and may exceed turns
    expect(['success', 'error_max_turns']).toContain(result.exitReason);

    // Verify the review was written
    const reviewPath = path.join(planDir, 'review-output.md');
    if (fs.existsSync(reviewPath)) {
      const review = fs.readFileSync(reviewPath, 'utf-8');
      expect(review.length).toBeGreaterThan(200);
    }
  }, 420_000);
});

// --- Plan Eng Review E2E ---

describeE2E('Plan Eng Review E2E', () => {
  let planDir: string;

  beforeAll(() => {
    planDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-plan-eng-'));
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });

    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);

    // Create a plan with more engineering detail
    fs.writeFileSync(path.join(planDir, 'plan.md'), `# Plan: Migrate Auth to JWT

## Context
Replace session-cookie auth with JWT tokens. Currently using express-session + Redis store.

## Changes
1. Add \`jsonwebtoken\` package
2. New middleware \`auth/jwt-verify.ts\` replacing \`auth/session-check.ts\`
3. Login endpoint returns { accessToken, refreshToken }
4. Refresh endpoint rotates tokens
5. Migration script to invalidate existing sessions

## Files Modified
| File | Change |
|------|--------|
| auth/jwt-verify.ts | NEW: JWT verification middleware |
| auth/session-check.ts | DELETED |
| routes/login.ts | Return JWT instead of setting cookie |
| routes/refresh.ts | NEW: Token refresh endpoint |
| middleware/index.ts | Swap session-check for jwt-verify |

## Error handling
- Expired token: 401 with \`token_expired\` code
- Invalid token: 401 with \`invalid_token\` code
- Refresh with revoked token: 403

## Not in scope
- OAuth/OIDC integration
- Rate limiting on refresh endpoint
`);

    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'add plan']);

    // Copy plan-eng-review skill
    fs.mkdirSync(path.join(planDir, 'plan-eng-review'), { recursive: true });
    fs.copyFileSync(
      path.join(ROOT, 'plan-eng-review', 'SKILL.md'),
      path.join(planDir, 'plan-eng-review', 'SKILL.md'),
    );
  });

  afterAll(() => {
    try { fs.rmSync(planDir, { recursive: true, force: true }); } catch {}
  });

  test('/plan-eng-review produces structured review output', async () => {
    const result = await runSkillTest({
      prompt: `Read plan-eng-review/SKILL.md for the review workflow.

Read plan.md — that's the plan to review. This is a standalone plan document, not a codebase — skip any codebase exploration steps.

Choose SMALL CHANGE mode. Skip any AskUserQuestion calls — this is non-interactive.
Write your complete review directly to ${planDir}/review-output.md

Focus on architecture, code quality, tests, and performance sections.`,
      workingDirectory: planDir,
      maxTurns: 15,
      timeout: 360_000,
      testName: 'plan-eng-review',
      runId,
    });

    logCost('/plan-eng-review', result);
    recordE2E('/plan-eng-review', 'Plan Eng Review E2E', result, {
      passed: ['success', 'error_max_turns'].includes(result.exitReason),
    });
    expect(['success', 'error_max_turns']).toContain(result.exitReason);

    // Verify the review was written
    const reviewPath = path.join(planDir, 'review-output.md');
    if (fs.existsSync(reviewPath)) {
      const review = fs.readFileSync(reviewPath, 'utf-8');
      expect(review.length).toBeGreaterThan(200);
    }
  }, 420_000);
});

// --- Retro E2E ---

describeE2E('Retro E2E', () => {
  let retroDir: string;

  beforeAll(() => {
    retroDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-retro-'));
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: retroDir, stdio: 'pipe', timeout: 5000 });

    // Create a git repo with varied commit history
    run('git', ['init']);
    run('git', ['config', 'user.email', 'dev@example.com']);
    run('git', ['config', 'user.name', 'Dev']);

    // Day 1 commits
    fs.writeFileSync(path.join(retroDir, 'app.ts'), 'console.log("hello");\n');
    run('git', ['add', 'app.ts']);
    run('git', ['commit', '-m', 'feat: initial app setup', '--date', '2026-03-10T09:00:00']);

    fs.writeFileSync(path.join(retroDir, 'auth.ts'), 'export function login() {}\n');
    run('git', ['add', 'auth.ts']);
    run('git', ['commit', '-m', 'feat: add auth module', '--date', '2026-03-10T11:00:00']);

    // Day 2 commits
    fs.writeFileSync(path.join(retroDir, 'app.ts'), 'import { login } from "./auth";\nconsole.log("hello");\nlogin();\n');
    run('git', ['add', 'app.ts']);
    run('git', ['commit', '-m', 'fix: wire up auth to app', '--date', '2026-03-11T10:00:00']);

    fs.writeFileSync(path.join(retroDir, 'test.ts'), 'import { test } from "bun:test";\ntest("login", () => {});\n');
    run('git', ['add', 'test.ts']);
    run('git', ['commit', '-m', 'test: add login test', '--date', '2026-03-11T14:00:00']);

    // Day 3 commits
    fs.writeFileSync(path.join(retroDir, 'api.ts'), 'export function getUsers() { return []; }\n');
    run('git', ['add', 'api.ts']);
    run('git', ['commit', '-m', 'feat: add users API endpoint', '--date', '2026-03-12T09:30:00']);

    fs.writeFileSync(path.join(retroDir, 'README.md'), '# My App\nA test application.\n');
    run('git', ['add', 'README.md']);
    run('git', ['commit', '-m', 'docs: add README', '--date', '2026-03-12T16:00:00']);

    // Copy retro skill
    fs.mkdirSync(path.join(retroDir, 'retro'), { recursive: true });
    fs.copyFileSync(
      path.join(ROOT, 'retro', 'SKILL.md'),
      path.join(retroDir, 'retro', 'SKILL.md'),
    );
  });

  afterAll(() => {
    try { fs.rmSync(retroDir, { recursive: true, force: true }); } catch {}
  });

  test('/retro produces analysis from git history', async () => {
    const result = await runSkillTest({
      prompt: `Read retro/SKILL.md for instructions on how to run a retrospective.

Run /retro for the last 7 days of this git repo. Skip any AskUserQuestion calls — this is non-interactive.
Write your retrospective report to ${retroDir}/retro-output.md

Analyze the git history and produce the narrative report as described in the SKILL.md.`,
      workingDirectory: retroDir,
      maxTurns: 30,
      timeout: 300_000,
      testName: 'retro',
      runId,
    });

    logCost('/retro', result);
    recordE2E('/retro', 'Retro E2E', result, {
      passed: ['success', 'error_max_turns'].includes(result.exitReason),
    });
    // Accept error_max_turns — retro does many git commands to analyze history
    expect(['success', 'error_max_turns']).toContain(result.exitReason);

    // Verify the retro was written
    const retroPath = path.join(retroDir, 'retro-output.md');
    if (fs.existsSync(retroPath)) {
      const retro = fs.readFileSync(retroPath, 'utf-8');
      expect(retro.length).toBeGreaterThan(100);
    }
  }, 420_000);
});

// --- QA-Only E2E (report-only, no fixes) ---

describeE2E('QA-Only skill E2E', () => {
  let qaOnlyDir: string;

  beforeAll(() => {
    testServer = testServer || startTestServer();
    qaOnlyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-only-'));
    setupBrowseShims(qaOnlyDir);

    // Copy qa-only skill files
    copyDirSync(path.join(ROOT, 'qa-only'), path.join(qaOnlyDir, 'qa-only'));

    // Copy qa templates (qa-only references qa/templates/qa-report-template.md)
    fs.mkdirSync(path.join(qaOnlyDir, 'qa', 'templates'), { recursive: true });
    fs.copyFileSync(
      path.join(ROOT, 'qa', 'templates', 'qa-report-template.md'),
      path.join(qaOnlyDir, 'qa', 'templates', 'qa-report-template.md'),
    );

    // Init git repo (qa-only checks for feature branch in diff-aware mode)
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: qaOnlyDir, stdio: 'pipe', timeout: 5000 });

    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);
    fs.writeFileSync(path.join(qaOnlyDir, 'index.html'), '<h1>Test</h1>\n');
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'initial']);
  });

  afterAll(() => {
    try { fs.rmSync(qaOnlyDir, { recursive: true, force: true }); } catch {}
  });

  test('/qa-only produces report without using Edit tool', async () => {
    const result = await runSkillTest({
      prompt: `IMPORTANT: The browse binary is already assigned below as B. Do NOT search for it or run the SKILL.md setup block — just use $B directly.

B="${browseBin}"

Read the file qa-only/SKILL.md for the QA-only workflow instructions.

Run a Quick QA test on ${testServer.url}/qa-eval.html
Do NOT use AskUserQuestion — run Quick tier directly.
Write your report to ${qaOnlyDir}/qa-reports/qa-only-report.md`,
      workingDirectory: qaOnlyDir,
      maxTurns: 35,
      allowedTools: ['Bash', 'Read', 'Write', 'Glob'],  // NO Edit — the critical guardrail
      timeout: 180_000,
      testName: 'qa-only-no-fix',
      runId,
    });

    logCost('/qa-only', result);

    // Verify Edit was not used — the critical guardrail for report-only mode.
    // Glob is read-only and may be used for file discovery (e.g. finding SKILL.md).
    const editCalls = result.toolCalls.filter(tc => tc.tool === 'Edit');
    if (editCalls.length > 0) {
      console.warn('qa-only used Edit tool:', editCalls.length, 'times');
    }

    const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
    recordE2E('/qa-only no-fix', 'QA-Only skill E2E', result, {
      passed: exitOk && editCalls.length === 0,
    });

    expect(editCalls).toHaveLength(0);

    // Accept error_max_turns — the agent doing thorough QA is not a failure
    expect(['success', 'error_max_turns']).toContain(result.exitReason);

    // Verify git working tree is still clean (no source modifications)
    const gitStatus = spawnSync('git', ['status', '--porcelain'], {
      cwd: qaOnlyDir, stdio: 'pipe',
    });
    const statusLines = gitStatus.stdout.toString().trim().split('\n').filter(
      (l: string) => l.trim() && !l.includes('.prompt-tmp') && !l.includes('.gstack/') && !l.includes('qa-reports/'),
    );
    expect(statusLines.filter((l: string) => l.startsWith(' M') || l.startsWith('M '))).toHaveLength(0);
  }, 240_000);
});

// --- QA Fix Loop E2E ---

describeE2E('QA Fix Loop E2E', () => {
  let qaFixDir: string;
  let qaFixServer: ReturnType<typeof Bun.serve> | null = null;

  beforeAll(() => {
    qaFixDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-fix-'));
    setupBrowseShims(qaFixDir);

    // Copy qa skill files
    copyDirSync(path.join(ROOT, 'qa'), path.join(qaFixDir, 'qa'));

    // Create a simple HTML page with obvious fixable bugs
    fs.writeFileSync(path.join(qaFixDir, 'index.html'), `<!DOCTYPE html>
<html lang="en">
<head><meta charset="utf-8"><title>Test App</title></head>
<body>
  <h1>Welcome to Test App</h1>
  <nav>
    <a href="/about">About</a>
    <a href="/nonexistent-broken-page">Help</a>  <!-- BUG: broken link -->
  </nav>
  <form id="contact">
    <input type="text" name="name" placeholder="Name">
    <input type="email" name="email" placeholder="Email">
    <button type="submit" disabled>Send</button>  <!-- BUG: permanently disabled -->
  </form>
  <img src="/missing-logo.png">  <!-- BUG: missing alt text -->
  <script>console.error("TypeError: Cannot read property 'map' of undefined");</script>  <!-- BUG: console error -->
</body>
</html>
`);

    // Init git repo with clean working tree
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: qaFixDir, stdio: 'pipe', timeout: 5000 });

    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'initial commit']);

    // Start a local server serving from the working directory so fixes are reflected on refresh
    qaFixServer = Bun.serve({
      port: 0,
      hostname: '127.0.0.1',
      fetch(req) {
        const url = new URL(req.url);
        let filePath = url.pathname === '/' ? '/index.html' : url.pathname;
        filePath = filePath.replace(/^\//, '');
        const fullPath = path.join(qaFixDir, filePath);
        if (!fs.existsSync(fullPath)) {
          return new Response('Not Found', { status: 404 });
        }
        const content = fs.readFileSync(fullPath, 'utf-8');
        return new Response(content, {
          headers: { 'Content-Type': 'text/html' },
        });
      },
    });
  });

  afterAll(() => {
    qaFixServer?.stop();
    try { fs.rmSync(qaFixDir, { recursive: true, force: true }); } catch {}
  });

  test('/qa fix loop finds bugs and commits fixes', async () => {
    const qaFixUrl = `http://127.0.0.1:${qaFixServer!.port}`;

    const result = await runSkillTest({
      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable like: B="${browseBin}"

Read the file qa/SKILL.md for the QA workflow instructions.

Run a Quick-tier QA test on ${qaFixUrl}
The source code for this page is at ${qaFixDir}/index.html — you can fix bugs there.
Do NOT use AskUserQuestion — run Quick tier directly.
Write your report to ${qaFixDir}/qa-reports/qa-report.md

This is a test+fix loop: find bugs, fix them in the source code, commit each fix, and re-verify.`,
      workingDirectory: qaFixDir,
      maxTurns: 40,
      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'],
      timeout: 300_000,
      testName: 'qa-fix-loop',
      runId,
    });

    logCost('/qa fix loop', result);
    recordE2E('/qa fix loop', 'QA Fix Loop E2E', result, {
      passed: ['success', 'error_max_turns'].includes(result.exitReason),
    });

    // Accept error_max_turns — fix loop may use many turns
    expect(['success', 'error_max_turns']).toContain(result.exitReason);

    // Verify at least one fix commit was made beyond the initial commit
    const gitLog = spawnSync('git', ['log', '--oneline'], {
      cwd: qaFixDir, stdio: 'pipe',
    });
    const commits = gitLog.stdout.toString().trim().split('\n');
    console.log(`/qa fix loop: ${commits.length} commits total (1 initial + ${commits.length - 1} fixes)`);
    expect(commits.length).toBeGreaterThan(1);

    // Verify Edit tool was used (agent actually modified source code)
    const editCalls = result.toolCalls.filter(tc => tc.tool === 'Edit');
    expect(editCalls.length).toBeGreaterThan(0);
  }, 360_000);
});

// --- Plan-Eng-Review Test-Plan Artifact E2E ---

describeE2E('Plan-Eng-Review Test-Plan Artifact E2E', () => {
  let planDir: string;
  let projectDir: string;

  beforeAll(() => {
    planDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-plan-artifact-'));
    const { spawnSync } = require('child_process');
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });

    run('git', ['init']);
    run('git', ['config', 'user.email', 'test@test.com']);
    run('git', ['config', 'user.name', 'Test']);

    // Create base commit on main
    fs.writeFileSync(path.join(planDir, 'app.ts'), 'export function greet() { return "hello"; }\n');
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'initial']);

    // Create feature branch with changes
    run('git', ['checkout', '-b', 'feature/add-dashboard']);
    fs.writeFileSync(path.join(planDir, 'dashboard.ts'), `export function Dashboard() {
  const data = fetchStats();
  return { users: data.users, revenue: data.revenue };
}
function fetchStats() {
  return fetch('/api/stats').then(r => r.json());
}
`);
    fs.writeFileSync(path.join(planDir, 'app.ts'), `import { Dashboard } from "./dashboard";
export function greet() { return "hello"; }
export function main() { return Dashboard(); }
`);
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'feat: add dashboard']);

    // Plan document
    fs.writeFileSync(path.join(planDir, 'plan.md'), `# Plan: Add Dashboard

## Changes
1. New \`dashboard.ts\` with Dashboard component and fetchStats API call
2. Updated \`app.ts\` to import and use Dashboard

## Architecture
- Dashboard fetches from \`/api/stats\` endpoint
- Returns user count and revenue metrics
`);
    run('git', ['add', 'plan.md']);
    run('git', ['commit', '-m', 'add plan']);

    // Copy plan-eng-review skill
    fs.mkdirSync(path.join(planDir, 'plan-eng-review'), { recursive: true });
    fs.copyFileSync(
      path.join(ROOT, 'plan-eng-review', 'SKILL.md'),
      path.join(planDir, 'plan-eng-review', 'SKILL.md'),
    );

    // Set up remote-slug shim and browse shims (plan-eng-review uses remote-slug for artifact path)
    setupBrowseShims(planDir);

    // Create project directory for artifacts
    projectDir = path.join(os.homedir(), '.gstack', 'projects', 'test-project');
    fs.mkdirSync(projectDir, { recursive: true });
  });

  afterAll(() => {
    try { fs.rmSync(planDir, { recursive: true, force: true }); } catch {}
    // Clean up test-plan artifacts (but not the project dir itself)
    try {
      const files = fs.readdirSync(projectDir);
      for (const f of files) {
        if (f.includes('test-plan')) {
          fs.unlinkSync(path.join(projectDir, f));
        }
      }
    } catch {}
  });

  test('/plan-eng-review writes test-plan artifact to ~/.gstack/projects/', async () => {
    // Count existing test-plan files before
    const beforeFiles = fs.readdirSync(projectDir).filter(f => f.includes('test-plan'));

    const result = await runSkillTest({
      prompt: `Read plan-eng-review/SKILL.md for the review workflow.

Read plan.md — that's the plan to review. This is a standalone plan with source code in app.ts and dashboard.ts.

Choose SMALL CHANGE mode. Skip any AskUserQuestion calls — this is non-interactive.

IMPORTANT: After your review, you MUST write the test-plan artifact as described in the "Test Plan Artifact" section of SKILL.md. The remote-slug shim is at ${planDir}/browse/bin/remote-slug.

Write your review to ${planDir}/review-output.md`,
      workingDirectory: planDir,
      maxTurns: 20,
      allowedTools: ['Bash', 'Read', 'Write', 'Glob', 'Grep'],
      timeout: 360_000,
      testName: 'plan-eng-review-artifact',
      runId,
    });

    logCost('/plan-eng-review artifact', result);
    recordE2E('/plan-eng-review test-plan artifact', 'Plan-Eng-Review Test-Plan Artifact E2E', result, {
      passed: ['success', 'error_max_turns'].includes(result.exitReason),
    });

    expect(['success', 'error_max_turns']).toContain(result.exitReason);

    // Verify test-plan artifact was written
    const afterFiles = fs.readdirSync(projectDir).filter(f => f.includes('test-plan'));
    const newFiles = afterFiles.filter(f => !beforeFiles.includes(f));
    console.log(`Test-plan artifacts: ${beforeFiles.length} before, ${afterFiles.length} after, ${newFiles.length} new`);

    if (newFiles.length > 0) {
      const content = fs.readFileSync(path.join(projectDir, newFiles[0]), 'utf-8');
      console.log(`Test-plan artifact (${newFiles[0]}): ${content.length} chars`);
      expect(content.length).toBeGreaterThan(50);
    } else {
      console.warn('No test-plan artifact found — agent may not have followed artifact instructions');
    }

    // Soft assertion: we expect an artifact but agent compliance is not guaranteed
    expect(newFiles.length).toBeGreaterThanOrEqual(1);
  }, 420_000);
});

// --- Deferred skill E2E tests (destructive or require interactive UI) ---

describeE2E('Deferred skill E2E', () => {
  // Ship is destructive: pushes to remote, creates PRs, modifies VERSION/CHANGELOG
  test.todo('/ship completes full workflow');

  // Setup-browser-cookies requires interactive browser picker UI
  test.todo('/setup-browser-cookies imports cookies');

  // Gstack-upgrade is destructive: modifies skill installation directory
  test.todo('/gstack-upgrade completes upgrade flow');
});

// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {
  if (evalCollector) {
    try {
      await evalCollector.finalize();
    } catch (err) {
      console.error('Failed to save eval results:', err);
    }
  }
});