cecli/tests/basic/test_coder.py at main · cecli-dev/cecli · GitHub

Repository navigation

History

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

import base64

import os

import tempfile

import uuid

from pathlib import Path

from unittest.mock import ANY, AsyncMock, MagicMock, patch

import git

import pytest

from cecli.coders import Coder

from cecli.coders.base_coder import FinishReasonLength, UnknownEditFormat

from cecli.commands import SwitchCoderSignal

from cecli.dump import dump # noqa: F401

from cecli.helpers.conversation import ConversationService

from cecli.helpers.conversation.tags import MessageTag

from cecli.io import InputOutput

from cecli.mcp import McpServerManager

from cecli.models import Model

from cecli.repo import GitRepo, GitRepoProxy

from cecli.sendchat import sanity_check_messages

from cecli.utils import GitTemporaryDirectory

class MockCoder:

"""Simple mock coder class for tests."""

def __init__(self):

self.uuid = str(uuid.uuid4())

class TestCoder:

@pytest.fixture(autouse=True)

def setup(self, gpt35_model):

self.uuid = str(uuid.uuid4())

self.GPT35 = gpt35_model

self.webbrowser_patcher = patch("webbrowser.open")

self.mock_webbrowser = self.webbrowser_patcher.start()

# Reset conversation system before each test

ConversationService.get_chunks(self).reset()

# Reset per-root singletons for test isolation

from cecli.helpers.file_system import FileSystemService

FileSystemService.reset_instance()

GitRepoProxy.reset_instances()

yield

# Cleanup after each test

self.webbrowser_patcher.stop()

# Reset conversation system after each test as well

ConversationService.get_chunks(self).reset()

async def test_stream_uses_active_model_streaming_support(self):

"""self.stream must follow the active model's streaming capability."""

with GitTemporaryDirectory():

io = MagicMock()

active_model = Model(self.GPT35.name)

active_model.streaming = False

with patch.object(Coder, "get_active_model", return_value=active_model):

coder = await Coder.create(self.GPT35, None, io, stream=True)

assert coder.stream is False

async def test_allowed_to_edit(self):

with GitTemporaryDirectory():

repo = git.Repo()

fname = Path("added.txt")

fname.touch()

repo.git.add(str(fname))

fname = Path("repo.txt")

fname.touch()

repo.git.add(str(fname))

repo.git.commit("-m", "init")

# YES!

# Use a completely mocked IO object instead of a real one

io = MagicMock()

io.confirm_ask = AsyncMock(return_value=True)

coder = await Coder.create(self.GPT35, None, io, fnames=["added.txt"])

assert await coder.allowed_to_edit("added.txt")

assert await coder.allowed_to_edit("repo.txt")

assert await coder.allowed_to_edit("new.txt")

assert "repo.txt" in str(coder.abs_fnames)

assert "new.txt" in str(coder.abs_fnames)

assert not coder.need_commit_before_edits

async def test_allowed_to_edit_no(self):

with GitTemporaryDirectory():

repo = git.Repo()

fname = Path("added.txt")

fname.touch()

repo.git.add(str(fname))

fname = Path("repo.txt")

fname.touch()

repo.git.add(str(fname))

repo.git.commit("-m", "init")

io = InputOutput(yes=False)

io.confirm_ask = AsyncMock(return_value=False)

coder = await Coder.create(self.GPT35, None, io, fnames=["added.txt"])

assert await coder.allowed_to_edit("added.txt")

assert not await coder.allowed_to_edit("repo.txt")

assert not await coder.allowed_to_edit("new.txt")

assert "repo.txt" not in str(coder.abs_fnames)

assert "new.txt" not in str(coder.abs_fnames)

assert not coder.need_commit_before_edits

async def test_allowed_to_edit_dirty(self):

with GitTemporaryDirectory():

repo = git.Repo()

fname = Path("added.txt")

fname.touch()

repo.git.add(str(fname))

repo.git.commit("-m", "init")

# say NO

io = InputOutput(yes=False)

coder = await Coder.create(self.GPT35, None, io, fnames=["added.txt"])

assert await coder.allowed_to_edit("added.txt")

assert not coder.need_commit_before_edits

fname.write_text("dirty!")

assert await coder.allowed_to_edit("added.txt")

assert coder.need_commit_before_edits

async def test_get_files_content(self):

tempdir = Path(tempfile.mkdtemp())

file1 = tempdir / "file1.txt"

file2 = tempdir / "file2.txt"

file1.touch()

file2.touch()

files = [file1, file2]

# Initialize the Coder object with the mocked IO and mocked repo

coder = await Coder.create(self.GPT35, None, io=InputOutput(), fnames=files)

content = coder.get_files_content()

all_file_names = content["chat_file_names"] | content["edit_file_names"]

assert "file1.txt" in all_file_names

assert "file2.txt" in all_file_names

async def test_check_for_filename_mentions(self):

with GitTemporaryDirectory():

repo = git.Repo()

mock_io = MagicMock()

mock_io.confirm_ask = AsyncMock(return_value=True)

fname1 = Path("file1.txt")

fname2 = Path("file2.py")

fname1.write_text("one\n")

fname2.write_text("two\n")

repo.git.add(str(fname1))

repo.git.add(str(fname2))

repo.git.commit("-m", "new")

mock_args = MagicMock(tui=False)

coder = await Coder.create(self.GPT35, None, mock_io, args=mock_args)

await coder.check_for_file_mentions("Please check file1.txt and file2.py")

expected_files = set(

[

str(Path(coder.root) / fname1),

str(Path(coder.root) / fname2),

]

)

assert coder.abs_fnames == expected_files

async def test_check_for_ambiguous_filename_mentions_of_longer_paths(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

mock_args = MagicMock(tui=False)

coder = await Coder.create(self.GPT35, None, io, args=mock_args)

fname = Path("file1.txt")

fname.touch()

other_fname = Path("other") / "file1.txt"

other_fname.parent.mkdir(parents=True, exist_ok=True)

other_fname.touch()

mock = MagicMock()

mock.return_value = set([str(fname), str(other_fname)])

coder.repo.get_tracked_files = mock

from cecli.helpers.file_system import FileSystemService

FileSystemService.get_instance().build()

await coder.check_for_file_mentions(f"Please check {fname}!")

assert coder.abs_fnames == {str(fname.resolve())}

async def test_skip_duplicate_basename_mentions(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

coder = await Coder.create(self.GPT35, None, io)

# Create files with same basename in different directories

fname1 = Path("dir1") / "file.txt"

fname2 = Path("dir2") / "file.txt"

fname3 = Path("dir3") / "unique.txt"

for fname in [fname1, fname2, fname3]:

fname.parent.mkdir(parents=True, exist_ok=True)

fname.touch()

# Add one file to chat

coder.add_rel_fname(str(fname1))

# Mock get_tracked_files to return all files

mock = MagicMock()

mock.return_value = set([str(fname1), str(fname2), str(fname3)])

coder.repo.get_tracked_files = mock

from cecli.helpers.file_system import FileSystemService

FileSystemService.get_instance().build()

# Check that file mentions of a pure basename skips files with duplicate basenames

mentioned = coder.get_file_mentions(f"Check {fname2.name} and {fname3}")

assert mentioned == {str(fname3)}

# Add a read-only file with same basename

coder.abs_read_only_fnames.add(str(fname2.resolve()))

mentioned = coder.get_file_mentions(f"Check {fname1} and {fname3}")

assert mentioned == {str(fname3)}

async def test_check_for_file_mentions_read_only(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

coder = await Coder.create(self.GPT35, None, io)

fname = Path("readonly_file.txt")

fname.touch()

coder.abs_read_only_fnames.add(str(fname.resolve()))

mock = MagicMock()

mock.return_value = set([str(fname)])

coder.repo.get_tracked_files = mock

result = await coder.check_for_file_mentions(f"Please check {fname}!")

assert result is None

assert coder.abs_fnames == set()

async def test_check_for_file_mentions_with_mocked_confirm(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False)

io.confirm_ask = AsyncMock(side_effect=[False, True, True])

mock_args = MagicMock(tui=False)

coder = await Coder.create(self.GPT35, None, io, args=mock_args)

coder.get_file_mentions = MagicMock(return_value=set(["file1.txt", "file2.txt"]))

await coder.check_for_file_mentions("Please check file1.txt for the info")

assert io.confirm_ask.call_count == 2

assert len(coder.abs_fnames) == 1

assert "file2.txt" in str(coder.abs_fnames)

io.confirm_ask.reset_mock()

await coder.check_for_file_mentions("Please check file1.txt and file2.txt again")

assert io.confirm_ask.call_count == 1

assert len(coder.abs_fnames) == 1

assert "file2.txt" in str(coder.abs_fnames)

assert "file1.txt" in coder.ignore_mentions

async def test_check_for_subdir_mention(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

mock_args = MagicMock(tui=False)

coder = await Coder.create(self.GPT35, None, io, args=mock_args)

fname = Path("other") / "file1.txt"

fname.parent.mkdir(parents=True, exist_ok=True)

fname.touch()

mock = MagicMock()

mock.return_value = set([str(fname)])

coder.repo.get_tracked_files = mock

from cecli.helpers.file_system import FileSystemService

FileSystemService.get_instance().build()

await coder.check_for_file_mentions(f"Please check `{fname}`")

assert coder.abs_fnames == {str(fname.resolve())}

async def test_get_file_mentions_various_formats(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

coder = await Coder.create(self.GPT35, None, io)

# Create test files

test_files = [

"file1.txt",

"file2.py",

"dir/nested_file.js",

"dir/subdir/deep_file.html",

"file99.txt",

"special_chars!@#.md",

]

# Pre-format the Windows path to avoid backslash issues in f-string expressions

windows_path = test_files[2].replace("/", "\\")

win_path3 = test_files[3].replace("/", "\\")

for fname in test_files:

fpath = Path(fname)

fpath.parent.mkdir(parents=True, exist_ok=True)

fpath.touch()

# Stage files and rebuild FileSystemService index

_gi = git.Repo()

for _f in test_files:

_gi.git.add(_f)

from cecli.helpers.file_system import FileSystemService

FileSystemService.get_instance().build()

# Mock get_addable_relative_files to return our test files

coder.get_addable_relative_files = MagicMock(return_value=set(test_files))

# Test different mention formats

test_cases = [

# Simple plain text mentions

(f"You should edit {test_files[0]} first", {test_files[0]}),

# Multiple files in plain text

(

f"Edit both {test_files[0]} and {test_files[1]}",

{test_files[0], test_files[1]},

# Files in backticks

(f"Check the file `{test_files[2]}`", {test_files[2]}),

# Files in code blocks

(f"```\n{test_files[3]}\n```", {test_files[3]}),

# Files in code blocks with language specifier

# (

# f"```python\nwith open('{test_files[1]}', 'r') as f:\n"

# f" data = f.read()\n```",

# {test_files[1]},

# ),

# Files with Windows-style paths

(f"Edit the file {windows_path}", {test_files[2]}),

# Files with different quote styles

(f'Check "{test_files[5]}" now', {test_files[5]}),

# All files in one complex message

(

f"First, edit `{test_files[0]}`. Then modify {test_files[1]}.\n"

f"```js\n// Update this file\nconst file = '{test_files[2]}';\n```\n"

f"Finally check {win_path3}"

{test_files[0], test_files[1], test_files[2], test_files[3]},

# Files mentioned in markdown bold format

(f"You should check **{test_files[0]}** for issues", {test_files[0]}),

(

f"Look at both **{test_files[1]}** and **{test_files[2]}**",

{test_files[1], test_files[2]},

(

f"The file **{win_path3}** needs updating",

{test_files[3]},

(

f"Files to modify:\n- **{test_files[0]}**\n- **{test_files[4]}**",

{test_files[0], test_files[4]},

]

for content, expected_mentions in test_cases:

mentioned_files = coder.get_file_mentions(content)

assert (

mentioned_files == expected_mentions

), f"Failed to extract mentions from: {content}"

async def test_get_file_mentions_multiline_backticks(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

coder = await Coder.create(self.GPT35, None, io)

# Create test files

test_files = [

"swebench/harness/test_spec/python.py",

"swebench/harness/test_spec/javascript.py",

]

for fname in test_files:

fpath = Path(fname)

fpath.parent.mkdir(parents=True, exist_ok=True)

fpath.touch()

# Stage files and rebuild FileSystemService index

_gi = git.Repo()

for _f in test_files:

_gi.git.add(_f)

from cecli.helpers.file_system import FileSystemService

FileSystemService.get_instance().build()

# Mock get_addable_relative_files to return our test files

coder.get_addable_relative_files = MagicMock(return_value=set(test_files))

# Input text with multiline backticked filenames

content = """

Could you please **add the following files to the chat**?

1. `swebench/harness/test_spec/python.py`

2. `swebench/harness/test_spec/javascript.py`

Once I have these, I can show you precisely how to do the thing.

"""

expected_mentions = {

"swebench/harness/test_spec/python.py",

"swebench/harness/test_spec/javascript.py",

}

mentioned_files = coder.get_file_mentions(content)

assert (

mentioned_files == expected_mentions

), f"Failed to extract mentions from multiline backticked content: {content}"

async def test_get_file_mentions_path_formats(self):

with GitTemporaryDirectory():

io = InputOutput(pretty=False, yes=True)

coder = await Coder.create(self.GPT35, None, io)

# Test cases with different path formats

test_cases = [

# Unix paths in content, Unix paths in get_addable_relative_files

("Check file1.txt and dir/file2.txt", ["file1.txt", "dir/file2.txt"]),

# Windows paths in content, Windows paths in get_addable_relative_files

("Check file1.txt and dir\\file2.txt", ["file1.txt", "dir\\file2.txt"]),

# Unix paths in content, Windows paths in get_addable_relative_files

("Check file1.txt and dir/file2.txt", ["file1.txt", "dir\\file2.txt"]),

# Windows paths in content, Unix paths in get_addable_relative_files

("Check file1.txt and dir\\file2.txt", ["file1.txt", "dir/file2.txt"]),

# Mixed paths in content, Unix paths in get_addable_relative_files

(

"Check file1.txt, dir/file2.txt, and other\\file3.txt",

["file1.txt", "dir/file2.txt", "other/file3.txt"],

# Mixed paths in content, Windows paths in get_addable_relative_files

(

"Check file1.txt, dir/file2.txt, and other\\file3.txt",

["file1.txt", "dir\\file2.txt", "other\\file3.txt"],

]

for content, addable_files in test_cases:

coder.get_addable_relative_files = MagicMock(return_value=set(addable_files))

mentioned_files = coder.get_file_mentions(content)

expected_files = set(addable_files)

assert (

mentioned_files == expected_files

), f"Failed for content: {content}, addable_files: {addable_files}"

async def test_run_with_file_deletion(self):

# Create a few temporary files

tempdir = Path(tempfile.mkdtemp())

file1 = tempdir / "file1.txt"

file2 = tempdir / "file2.txt"

file1.touch()

file2.touch()

files = [file1, file2]

coder = await Coder.create(self.GPT35, None, io=InputOutput(), fnames=files)

async def mock_send(*args, **kwargs):

coder.partial_response_content = "ok"

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

coder.send = mock_send

# Call the run method with a message

await coder.run(with_message="hi")

assert len(coder.abs_fnames) == 2

file1.unlink()

# Call the run method again with a message

await coder.run(with_message="hi")

assert len(coder.abs_fnames) == 1

async def test_run_with_file_unicode_error(self):

# Create a few temporary files

_, file1 = tempfile.mkstemp()

_, file2 = tempfile.mkstemp()

files = [file1, file2]

coder = await Coder.create(self.GPT35, None, io=InputOutput(), fnames=files)

async def mock_send(*args, **kwargs):

coder.partial_response_content = "ok"

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

coder.send = mock_send

# Call the run method with a message

await coder.run(with_message="hi")

assert len(coder.abs_fnames) == 2

# Write some non-UTF8 text into the file

with open(file1, "wb") as f:

f.write(b"\x80abc")

# Call the run method again with a message

await coder.run(with_message="hi")

assert len(coder.abs_fnames) == 2

async def test_choose_fence(self):

# Create a few temporary files

_, file1 = tempfile.mkstemp()

with open(file1, "wb") as f:

f.write(b"this contains\n```\nbackticks")

files = [file1]

coder = await Coder.create(self.GPT35, None, io=InputOutput(), fnames=files)

async def mock_send(*args, **kwargs):

coder.partial_response_content = "ok"

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

coder.send = mock_send

# Call the run method with a message

await coder.run(with_message="hi")

assert coder.fence[0] != "```"

async def test_run_with_file_utf_unicode_error(self):

"make sure that we honor InputOutput(encoding) and don't just assume utf-8"

encoding = "utf-16"

_, file1 = tempfile.mkstemp()

_, file2 = tempfile.mkstemp()

files = [file1, file2]

# Initialize the Coder object with the mocked IO and mocked repo

coder = await Coder.create(

self.GPT35,

None,

io=InputOutput(encoding=encoding),

fnames=files,

)

async def mock_send(*args, **kwargs):

coder.partial_response_content = "ok"

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

coder.send = mock_send

# Call the run method with a message

await coder.run(with_message="hi")

assert len(coder.abs_fnames) == 2

some_content_which_will_error_if_read_with_encoding_utf8 = "ÅÍÎÏ".encode(encoding)

with open(file1, "wb") as f:

f.write(some_content_which_will_error_if_read_with_encoding_utf8)

await coder.run(with_message="hi")

# both files should still be here

assert len(coder.abs_fnames) == 2

async def test_new_file_edit_one_commit(self):

"""A new file should get pre-committed before the GPT edit commit"""

with GitTemporaryDirectory():

repo = git.Repo()

fname = Path("file.txt")

io = InputOutput(yes=True)

io.tool_warning = MagicMock()

coder = await Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)])

assert fname.exists()

# make sure it was not committed

with pytest.raises(git.exc.GitCommandError):

list(repo.iter_commits(repo.active_branch.name))

async def mock_send(*args, **kwargs):

coder.partial_response_content = f"""

Do this:

{str(fname)}

<<<<<<< SEARCH

=======

new

>>>>>>> REPLACE

"""

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

coder.send = mock_send

coder.repo.get_commit_message = AsyncMock(return_value="commit message")

await coder.run(with_message="hi")

content = fname.read_text()

assert content == "new\n"

num_commits = len(list(repo.iter_commits(repo.active_branch.name)))

assert num_commits == 2

async def test_only_commit_gpt_edited_file(self):

"""

Only commit file that gpt edits, not other dirty files.

Also ensure commit msg only depends on diffs from the GPT edited file.

"""

with GitTemporaryDirectory():

repo = git.Repo()

fname1 = Path("file1.txt")

fname2 = Path("file2.txt")

fname1.write_text("one\n")

fname2.write_text("two\n")

repo.git.add(str(fname1))

repo.git.add(str(fname2))

repo.git.commit("-m", "new")

# DIRTY!

fname1.write_text("ONE\n")

io = InputOutput(yes=True)

coder = await Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname1), str(fname2)])

async def mock_send(*args, **kwargs):

coder.partial_response_content = f"""

Do this:

{str(fname2)}

<<<<<<< SEARCH

two

=======

TWO

>>>>>>> REPLACE

"""

coder.partial_response_function_call = dict()

return

yield

def mock_get_commit_message(diffs, context, user_language=None):

assert "one" not in diffs

assert "ONE" not in diffs

return "commit message"

coder.send = mock_send

coder.repo.get_commit_message = MagicMock(side_effect=mock_get_commit_message)

await coder.run(with_message="hi")

content = fname2.read_text()

assert content == "TWO\n"

assert repo.is_dirty(path=str(fname1))

async def test_gpt_edit_to_dirty_file(self):

"""A dirty file should be committed before the GPT edits are committed"""

with GitTemporaryDirectory():

repo = git.Repo()

fname = Path("file.txt")

fname.write_text("one\n")

repo.git.add(str(fname))

fname2 = Path("other.txt")

fname2.write_text("other\n")

repo.git.add(str(fname2))

repo.git.commit("-m", "new")

# dirty

fname.write_text("two\n")

fname2.write_text("OTHER\n")

io = InputOutput(yes=True)

coder = await Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)])

async def mock_send(*args, **kwargs):

coder.partial_response_content = f"""

Do this:

{str(fname)}

<<<<<<< SEARCH

two

=======

three

>>>>>>> REPLACE

"""

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

saved_diffs = []

async def mock_get_commit_message(diffs, context, user_language=None, coder=None):

saved_diffs.append(diffs)

return "commit message"

coder.repo.get_commit_message = mock_get_commit_message

coder.send = mock_send

await coder.run(with_message="hi")

content = fname.read_text()

assert content == "three\n"

num_commits = len(list(repo.iter_commits(repo.active_branch.name)))

assert num_commits == 3

diff = repo.git.diff(["HEAD~2", "HEAD~1"])

assert "one" in diff

assert "two" in diff

assert "three" not in diff

assert "other" not in diff

assert "OTHER" not in diff

diff = saved_diffs[0]

assert "one" in diff

assert "two" in diff

assert "three" not in diff

assert "other" not in diff

assert "OTHER" not in diff

diff = repo.git.diff(["HEAD~1", "HEAD"])

assert "one" not in diff

assert "two" in diff

assert "three" in diff

assert "other" not in diff

assert "OTHER" not in diff

diff = saved_diffs[1]

assert "one" not in diff

assert "two" in diff

assert "three" in diff

assert "other" not in diff

assert "OTHER" not in diff

assert len(saved_diffs) == 2

async def test_gpt_edit_to_existing_file_not_in_repo(self):

with GitTemporaryDirectory():

repo = git.Repo()

fname = Path("file.txt")

fname.write_text("one\n")

fname2 = Path("other.txt")

fname2.write_text("other\n")

repo.git.add(str(fname2))

repo.git.commit("-m", "initial")

io = InputOutput(yes=True)

coder = await Coder.create(self.GPT35, "diff", io=io, fnames=[str(fname)])

async def mock_send(*args, **kwargs):

coder.partial_response_content = f"""

Do this:

{str(fname)}

<<<<<<< SEARCH

one

=======

two

>>>>>>> REPLACE

"""

coder.partial_response_function_call = dict()

coder.partial_response_chunks = []

return

yield

saved_diffs = []

async def mock_get_commit_message(diffs, context, user_language=None, coder=None):

saved_diffs.append(diffs)

return "commit message"

coder.repo.get_commit_message = mock_get_commit_message

coder.send = mock_send

await coder.run(with_message="hi")

content = fname.read_text()

assert content == "two\n"

diff = saved_diffs[0]

assert "file.txt" in diff

async def test_skip_cecli_ignored_files(self):

with GitTemporaryDirectory():

repo = git.Repo()

fname1 = "ignoreme1.txt"

fname2 = "ignoreme2.txt"

fname3 = "dir/ignoreme3.txt"

Path(fname2).touch()

repo.git.add(str(fname2))

repo.git.commit("-m", "initial")

io = InputOutput(yes=True)

fnames = [fname1, fname2, fname3]

aignore = Path("cecli.ignore")

aignore.write_text(f"{fname1}\n{fname2}\ndir\n")

repo = GitRepo(

io,

fnames,

None,

cecli_ignore_file=str(aignore),

)

coder = await Coder.create(

self.GPT35,

None,

io,

fnames=fnames,

repo=repo,

)

assert fname1 not in str(coder.abs_fnames)

assert fname2 not in str(coder.abs_fnames)

assert fname3 not in str(coder.abs_fnames)

async def test_skip_gitignored_files_on_init(self):

with GitTemporaryDirectory() as _:

repo_path = Path(".")

repo = git.Repo.init(repo_path)

ignored_file = repo_path / "ignored_by_git.txt"

ignored_file.write_text("This file should be ignored by git.")

regular_file = repo_path / "regular_file.txt"

regular_file.write_text("This is a regular file.")

gitignore_content = "ignored_by_git.txt\n"

(repo_path / ".gitignore").write_text(gitignore_content)

repo.index.add([str(regular_file), ".gitignore"])

repo.index.commit("Initial commit with gitignore and regular file")

mock_io = MagicMock()

mock_io.tool_warning = MagicMock()

fnames_to_add = [str(ignored_file), str(regular_file)]

coder = await Coder.create(self.GPT35, None, mock_io, fnames=fnames_to_add)

assert str(ignored_file.resolve()) not in coder.abs_fnames

assert str(regular_file.resolve()) in coder.abs_fnames

_ = any(

call.kwargs.get("message")

== f"Skipping {ignored_file.name} that matches gitignore spec."

for call in mock_io.tool_warning.call_args_list

)

async def test_check_for_urls(self):

io = InputOutput(yes=True)

mock_args = MagicMock()

mock_args.yes_always_commands = True

mock_args.disable_scraping = False

coder = await Coder.create(self.GPT35, None, io=io, args=mock_args)

# Mock the execute command to return scraped content

async def mock_execute(cmd_name, url, **kwargs):

if cmd_name == "web" and kwargs.get("return_content"):

return f"Scraped content from {url}"

return None

coder.commands.execute = mock_execute

# Test various URL formats

test_cases = [

("Check http://example.com, it's cool", "http://example.com"),

(

"Visit https://www.example.com/page and see stuff",

"https://www.example.com/page",

(

"Go to http://subdomain.example.com:8080/path?query=value, or not",

"http://subdomain.example.com:8080/path?query=value",

(

"See https://example.com/path#fragment for example",

"https://example.com/path#fragment",

("Look at http://localhost:3000", "http://localhost:3000"),

(

"View https://example.com/setup#whatever",

"https://example.com/setup#whatever",

("Open http://127.0.0.1:8000/api/v1/", "http://127.0.0.1:8000/api/v1/"),

(

"Try https://example.com/path/to/page.html?param1=value1&param2=value2",

"https://example.com/path/to/page.html?param1=value1&param2=value2",

(

"Access http://user:password@example.com",

"http://user:password@example.com",

(

"Use https://example.com/path_(with_parentheses)",

"https://example.com/path_(with_parentheses)",

]

for input_text, expected_url in test_cases:

result = await coder.check_for_urls(input_text)

assert expected_url in result

# Test cases from the GitHub issue

issue_cases = [

("check http://localhost:3002, there is an error", "http://localhost:3002"),

(

"can you check out https://example.com/setup#whatever",

"https://example.com/setup#whatever",

]

for input_text, expected_url in issue_cases:

result = await coder.check_for_urls(input_text)

assert expected_url in result

# Test case with multiple URLs

multi_url_input = "Check http://example1.com and https://example2.com/page"

result = await coder.check_for_urls(multi_url_input)

assert "http://example1.com" in result

assert "https://example2.com/page" in result

# Test case with no URL

no_url_input = "This text contains no URL"

result = await coder.check_for_urls(no_url_input)

assert result == no_url_input

# Test case with the same URL appearing multiple times

repeated_url_input = (

"Check https://example.com, then https://example.com again, and https://example.com one"

" more time"

)

result = await coder.check_for_urls(repeated_url_input)

# the original 3 in the input text, plus 1 more for the scraped text

assert result.count("https://example.com") == 4

assert "https://example.com" in result

View remainder of file in raw view

cecli/tests/basic/test_coder.py at main · cecli-dev/cecli · GitHub

Repository navigation

Expand file tree

Breadcrumbs

test_coder.py

Latest commit

History

Breadcrumbs

test_coder.py

File metadata and controls