File size: 44,015 Bytes
329b91e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Python Dependency Compatibility Board
A tool to parse, analyze, and resolve Python package dependencies.
"""

import re
import json
import tempfile
import subprocess
from pathlib import Path
from typing import List, Dict, Tuple, Optional, Set
from difflib import get_close_matches
import requests
from packaging.requirements import Requirement
from packaging.specifiers import SpecifierSet
from packaging.version import Version

# Import ML models (with graceful fallback)
try:
    from ml_models import ConflictPredictor, PackageEmbeddings
    ML_AVAILABLE = True
except ImportError:
    ML_AVAILABLE = False
    print("Warning: ML models not available. Some features will be disabled.")


class DependencyParser:
    """Parse requirements.txt and library lists into structured dependencies."""
    
    @staticmethod
    def parse_requirements_text(text: str) -> List[Dict]:
        """Parse requirements.txt content into structured format."""
        dependencies = []
        seen_packages = {}
        
        for line in text.strip().split('\n'):
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            
            # Remove comments
            if '#' in line:
                line = line[:line.index('#')].strip()
            
            try:
                req = Requirement(line)
                package_name = req.name.lower()
                
                # Handle duplicate packages
                if package_name in seen_packages:
                    # Merge or warn about duplicates
                    existing = seen_packages[package_name]
                    if existing['specifier'] != str(req.specifier):
                        dependencies.append({
                            'package': package_name,
                            'specifier': str(req.specifier) if req.specifier else '',
                            'extras': list(req.extras) if req.extras else [],
                            'marker': str(req.marker) if req.marker else '',
                            'original': line,
                            'conflict': f"Duplicate: {existing['original']} vs {line}"
                        })
                    continue
                
                dep = {
                    'package': package_name,
                    'specifier': str(req.specifier) if req.specifier else '',
                    'extras': list(req.extras) if req.extras else [],
                    'marker': str(req.marker) if req.marker else '',
                    'original': line,
                    'conflict': None
                }
                dependencies.append(dep)
                seen_packages[package_name] = dep
            except Exception as e:
                # Handle malformed lines
                dependencies.append({
                    'package': line.split('==')[0].split('>=')[0].split('<=')[0].split('[')[0].strip(),
                    'specifier': '',
                    'extras': [],
                    'marker': '',
                    'original': line,
                    'conflict': f"Parse error: {str(e)}"
                })
        
        return dependencies
    
    @staticmethod
    def parse_library_list(text: str) -> List[Dict]:
        """Parse a simple list of library names."""
        dependencies = []
        for line in text.strip().split('\n'):
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            
            # Extract package name (remove version specifiers if present)
            package_name = re.split(r'[<>=!]', line)[0].strip()
            package_name = re.split(r'\[', package_name)[0].strip()
            
            if package_name:
                dependencies.append({
                    'package': package_name.lower(),
                    'specifier': '',
                    'extras': [],
                    'marker': '',
                    'original': package_name,
                    'conflict': None
                })
        
        return dependencies


class DependencyResolver:
    """Resolve dependencies and check compatibility."""
    
    def __init__(self, python_version: str = "3.10", platform: str = "any", device: str = "cpu"):
        self.python_version = python_version
        self.platform = platform
        self.device = device
    
    def build_dependency_graph(self, dependencies: List[Dict], deep_mode: bool = False) -> Dict:
        """Build dependency graph (simplified - in production would query PyPI)."""
        graph = {
            'nodes': {},
            'edges': [],
            'conflicts': []
        }
        
        for dep in dependencies:
            package = dep['package']
            graph['nodes'][package] = {
                'specifier': dep['specifier'],
                'extras': dep['extras'],
                'marker': dep['marker'],
                'conflict': dep.get('conflict')
            }
            
            if dep.get('conflict'):
                graph['conflicts'].append({
                    'package': package,
                    'reason': dep['conflict']
                })
        
        # In deep mode, would fetch transitive dependencies from PyPI
        # For now, we'll use a simplified approach
        
        return graph
    
    def check_compatibility(self, graph: Dict) -> Tuple[bool, List[str]]:
        """Check version compatibility across the graph."""
        issues = []
        
        # Check for duplicate package conflicts
        for conflict in graph['conflicts']:
            issues.append(f"Conflict in {conflict['package']}: {conflict['reason']}")
        
        # Check known compatibility issues
        nodes = graph['nodes']
        
        # PyTorch Lightning + PyTorch compatibility
        if 'pytorch-lightning' in nodes and 'torch' in nodes:
            pl_spec = nodes['pytorch-lightning']['specifier']
            torch_spec = nodes['torch']['specifier']
            
            # Simplified check - in production would parse versions properly
            if '==2.' in pl_spec or '>=2.' in pl_spec:
                if '==1.' in torch_spec or ('<2.' in torch_spec and '==1.' in torch_spec):
                    issues.append("pytorch-lightning>=2.0 requires torch>=2.0, but torch<2.0 is specified")
        
        # FastAPI + Pydantic compatibility
        if 'fastapi' in nodes and 'pydantic' in nodes:
            fastapi_spec = nodes['fastapi']['specifier']
            pydantic_spec = nodes['pydantic']['specifier']
            
            if '==0.78' in fastapi_spec or '==0.7' in fastapi_spec:
                if '==2.' in pydantic_spec or '>=2.' in pydantic_spec:
                    issues.append("fastapi==0.78.x requires pydantic v1, but pydantic v2 is specified")
        
        # TensorFlow + Keras compatibility
        if 'tensorflow' in nodes and 'keras' in nodes:
            tf_spec = nodes['tensorflow']['specifier']
            keras_spec = nodes['keras']['specifier']
            
            if '==1.' in tf_spec:
                if '==3.' in keras_spec or '>=3.' in keras_spec:
                    issues.append("keras>=3.0 requires TensorFlow 2.x, but TensorFlow 1.x is specified")
        
        return len(issues) == 0, issues
    
    def resolve_dependencies(
        self, 
        dependencies: List[Dict], 
        strategy: str = "latest_compatible"
    ) -> Tuple[str, List[str]]:
        """Resolve dependencies using specified strategy."""
        # Remove duplicates and conflicts
        seen_packages = {}
        clean_dependencies = []
        
        for dep in dependencies:
            if dep.get('conflict'):
                continue
            
            package = dep['package']
            if package in seen_packages:
                # Keep the one with more specific version if available
                existing = seen_packages[package]
                if dep['specifier'] and not existing['specifier']:
                    clean_dependencies.remove(existing)
                    clean_dependencies.append(dep)
                    seen_packages[package] = dep
                continue
            
            clean_dependencies.append(dep)
            seen_packages[package] = dep
        
        # Create a temporary requirements file
        with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
            req_lines = []
            for dep in clean_dependencies:
                req_lines.append(dep['original'])
            f.write('\n'.join(req_lines))
            temp_req_file = f.name
        
        warnings = []
        
        try:
            # Try using pip's resolver with --dry-run and --report (pip 22.2+)
            result = subprocess.run(
                ['pip', 'install', '--dry-run', '--report', '-', '-r', temp_req_file],
                capture_output=True,
                text=True,
                timeout=60
            )
            
            if result.returncode == 0 and result.stdout.strip():
                # Parse the JSON report
                try:
                    report = json.loads(result.stdout)
                    resolved = []
                    for package in report.get('install', []):
                        name = package.get('metadata', {}).get('name', '')
                        version = package.get('metadata', {}).get('version', '')
                        if name and version:
                            resolved.append(f"{name}=={version}")
                    
                    if resolved:
                        return '\n'.join(sorted(resolved)), warnings
                except json.JSONDecodeError:
                    warnings.append("Could not parse pip resolution report. Using original requirements.")
                except Exception as e:
                    warnings.append(f"Error parsing resolution: {str(e)}")
            
            # Fallback: try pip-compile if available
            try:
                result = subprocess.run(
                    ['pip-compile', '--dry-run', '--output-file', '-', temp_req_file],
                    capture_output=True,
                    text=True,
                    timeout=60
                )
                if result.returncode == 0:
                    return result.stdout.strip(), warnings
            except FileNotFoundError:
                pass
            except Exception:
                pass
            
            # Final fallback: return cleaned original requirements
            resolved_lines = []
            for dep in clean_dependencies:
                line = dep['original']
                # Apply strategy-based modifications
                if strategy == "stable/pinned" and not dep['specifier']:
                    # In a real implementation, would query PyPI for latest stable
                    line = f"{dep['package']}  # Version not specified"
                elif strategy == "keep_existing_pins":
                    # Keep as-is
                    pass
                resolved_lines.append(line)
            
            if not warnings:
                warnings.append("Using original requirements. For full resolution, ensure pip>=22.2 is installed.")
            
            return '\n'.join(resolved_lines), warnings
        
        except subprocess.TimeoutExpired:
            warnings.append("Resolution timed out. Showing original requirements.")
            return '\n'.join([d['original'] for d in clean_dependencies]), warnings
        except Exception as e:
            warnings.append(f"Resolution error: {str(e)}")
            return '\n'.join([d['original'] for d in clean_dependencies]), warnings
        finally:
            Path(temp_req_file).unlink(missing_ok=True)


class CatalogValidator:
    """Validate package names against a simple ground-truth catalog."""

    def __init__(self, catalog_path: Path = Path("data/package_name_catalog.json"), use_ml: bool = True):
        self.catalog_path = catalog_path
        self.valid_packages: Set[str] = set()
        self.invalid_packages: Set[str] = set()
        self.use_ml = use_ml and ML_AVAILABLE
        self.embeddings = None
        
        self._load_catalog()
        
        # Load embeddings if available
        if self.use_ml:
            try:
                self.embeddings = PackageEmbeddings()
            except Exception as e:
                print(f"Warning: Could not load embeddings: {e}")
                self.use_ml = False

    def _load_catalog(self) -> None:
        if not self.catalog_path.exists():
            return
        try:
            data = json.loads(self.catalog_path.read_text())
            self.valid_packages = {p.lower() for p in data.get("valid_packages", [])}
            self.invalid_packages = {p.lower() for p in data.get("invalid_packages", [])}
        except Exception as exc:
            # Keep going even if catalog is malformed
            print(f"Warning: could not read catalog {self.catalog_path}: {exc}")

    def suggest_correction(self, package_name: str, cutoff: float = 0.6) -> Optional[str]:
        """Suggest a corrected package name using fuzzy matching and embeddings."""
        if not self.valid_packages:
            return None
        
        package_lower = package_name.lower()
        
        # If it's already valid, no correction needed
        if package_lower in self.valid_packages:
            return None
        
        # Try ML-based embedding similarity first (more accurate)
        if self.use_ml and self.embeddings:
            try:
                best_match = self.embeddings.get_best_match(package_name, threshold=0.7)
                if best_match and best_match in self.valid_packages:
                    return best_match
            except Exception:
                pass
        
        # Fallback to fuzzy matching
        matches = get_close_matches(
            package_lower,
            list(self.valid_packages),
            n=1,
            cutoff=cutoff
        )
        
        if matches:
            return matches[0]
        return None
    
    def check_and_correct_packages(self, dependencies: List[Dict], auto_correct: bool = True) -> Tuple[List[Dict], List[str]]:
        """Check packages and optionally correct spelling mistakes.
        
        Returns:
            Tuple of (corrected_dependencies, warnings)
        """
        corrected_deps = []
        warnings: List[str] = []
        seen: Set[str] = set()
        max_warnings = 15

        for dep in dependencies:
            package = dep["package"]
            package_lower = package.lower()
            
            if package_lower in seen:
                corrected_deps.append(dep)
                continue
            seen.add(package_lower)

            # Check if it's explicitly invalid
            if self.invalid_packages and package_lower in self.invalid_packages:
                warnings.append(f"Package '{package}' is flagged as invalid in the catalog.")
                if len(warnings) >= max_warnings:
                    corrected_deps.append(dep)
                    continue
                
                # Try to suggest a correction
                suggestion = self.suggest_correction(package)
                if suggestion:
                    if auto_correct:
                        corrected_dep = dep.copy()
                        corrected_dep['package'] = suggestion
                        corrected_dep['original'] = corrected_dep['original'].replace(package, suggestion, 1)
                        corrected_deps.append(corrected_dep)
                        warnings.append(f"  → Auto-corrected to '{suggestion}'")
                    else:
                        warnings.append(f"  → Did you mean '{suggestion}'?")
                else:
                    corrected_deps.append(dep)
                continue

            # Check if it's not in valid catalog and suggest correction
            if self.valid_packages and package_lower not in self.valid_packages:
                suggestion = self.suggest_correction(package)
                if suggestion:
                    if auto_correct:
                        corrected_dep = dep.copy()
                        corrected_dep['package'] = suggestion
                        corrected_dep['original'] = corrected_dep['original'].replace(package, suggestion, 1)
                        corrected_deps.append(corrected_dep)
                        warnings.append(f"Package '{package}' not found. Auto-corrected to '{suggestion}'")
                    else:
                        warnings.append(f"Package '{package}' not found. Did you mean '{suggestion}'?")
                    if len(warnings) >= max_warnings:
                        break
                else:
                    warnings.append(
                        f"Package '{package}' is not in the curated valid catalog. Check for typos or private packages."
                    )
                    corrected_deps.append(dep)
                    if len(warnings) >= max_warnings:
                        break
            else:
                # Package is valid, keep as-is
                corrected_deps.append(dep)

        if len(warnings) >= max_warnings:
            warnings.append("Additional potential catalog issues omitted for brevity.")

        return corrected_deps, warnings
    
    def check_packages(self, dependencies: List[Dict]) -> List[str]:
        """Return warnings for packages that look suspicious or explicitly invalid."""
        _, warnings = self.check_and_correct_packages(dependencies, auto_correct=False)
        return warnings


class ExplanationEngine:
    """Generate intelligent explanations for dependency conflicts using LLM."""
    
    def __init__(self, use_llm: bool = True):
        """
        Initialize explanation engine.
        
        Args:
            use_llm: If True, uses Hugging Face Inference API (free tier)
                    If False, uses rule-based explanations only
        """
        self.use_llm = use_llm
        # Using Hugging Face Inference API (free tier)
        self.api_url = "https://api-inference.huggingface.co/models/gpt2"
        self.headers = {"Content-Type": "application/json"}
    
    def generate_explanation(self, conflict: Dict, dependencies: List[Dict]) -> Dict:
        """
        Generate a detailed explanation for a conflict.
        
        Args:
            conflict: Conflict dictionary with type, packages, message, etc.
            dependencies: Full list of dependencies for context
            
        Returns:
            Dictionary with explanation, why_it_happens, how_to_fix
        """
        # Build context about the conflict
        conflict_type = conflict.get('type', 'unknown')
        packages = conflict.get('packages', [conflict.get('package', 'unknown')])
        message = conflict.get('message', '')
        details = conflict.get('details', {})
        
        # Create prompt for LLM
        prompt = self._create_prompt(conflict, dependencies)
        
        # Get LLM explanation
        explanation_text = self._call_llm(prompt) if self.use_llm else self._fallback_explanation(prompt)
        
        # Parse and structure the explanation
        return {
            'summary': message,
            'explanation': explanation_text,
            'why_it_happens': self._extract_why(explanation_text, conflict),
            'how_to_fix': self._extract_fix(explanation_text, conflict),
            'packages_involved': packages,
            'severity': conflict.get('severity', 'medium')
        }
    
    def _create_prompt(self, conflict: Dict, dependencies: List[Dict]) -> str:
        """Create a prompt for the LLM."""
        conflict_type = conflict.get('type', 'unknown')
        packages = conflict.get('packages', [conflict.get('package', 'unknown')])
        message = conflict.get('message', '')
        details = conflict.get('details', {})
        
        # Get relevant dependency info
        relevant_deps = [d for d in dependencies if d['package'] in packages]
        
        prompt = f"""You are a Python dependency expert. Explain this dependency conflict clearly:

Conflict: {message}
Type: {conflict_type}
Packages involved: {', '.join(packages)}

Dependency details:
"""
        for dep in relevant_deps:
            prompt += f"- {dep['package']}: {dep['specifier'] or 'no version specified'}\n"
        
        if details:
            prompt += f"\nVersion constraints: {json.dumps(details)}\n"
        
        prompt += """
Provide a clear, concise explanation that:
1. Explains what the conflict is in simple terms
2. Explains why this conflict happens (technical reason)
3. Suggests how to fix it (specific version recommendations)

Keep it under 150 words and use plain language.
"""
        return prompt
    
    def _call_llm(self, prompt: str) -> str:
        """
        Call LLM API to generate explanation.
        Falls back to rule-based explanation if API fails.
        """
        try:
            # Try Hugging Face Inference API (free tier)
            payload = {
                "inputs": prompt,
                "parameters": {
                    "max_new_tokens": 200,
                    "temperature": 0.7,
                    "return_full_text": False
                }
            }
            
            response = requests.post(
                self.api_url,
                headers=self.headers,
                json=payload,
                timeout=10
            )
            
            if response.status_code == 200:
                result = response.json()
                if isinstance(result, list) and len(result) > 0:
                    generated_text = result[0].get('generated_text', '')
                    if generated_text:
                        return generated_text.strip()
            
            # If API fails, fall back to rule-based
            return self._fallback_explanation(prompt)
        
        except Exception as e:
            # Fall back to rule-based explanation
            return self._fallback_explanation(prompt)
    
    def _fallback_explanation(self, prompt: str) -> str:
        """Generate rule-based explanation when LLM is unavailable."""
        # Extract key info from prompt
        if "pytorch-lightning" in prompt.lower() and "torch" in prompt.lower():
            return """PyTorch Lightning 2.0+ requires PyTorch 2.0 or higher because it uses new PyTorch APIs and features that don't exist in version 1.x. The conflict happens because you're trying to use a newer version of PyTorch Lightning with an older version of PyTorch. To fix this, either upgrade PyTorch to 2.0+ or downgrade PyTorch Lightning to 1.x."""
        
        elif "fastapi" in prompt.lower() and "pydantic" in prompt.lower():
            return """FastAPI 0.78.x was built for Pydantic v1, which has a different API than Pydantic v2. The conflict occurs because Pydantic v2 introduced breaking changes that FastAPI 0.78 doesn't support. To fix this, either upgrade FastAPI to 0.99+ (which supports Pydantic v2) or downgrade Pydantic to v1.x."""
        
        elif "tensorflow" in prompt.lower() and "keras" in prompt.lower():
            return """Keras 3.0+ requires TensorFlow 2.x because it was redesigned to work with TensorFlow 2's eager execution and new features. TensorFlow 1.x uses a different execution model that Keras 3.0 doesn't support. To fix this, upgrade TensorFlow to 2.x or downgrade Keras to 2.x."""
        
        elif "duplicate" in prompt.lower():
            return """You have the same package specified multiple times with different versions. This creates ambiguity about which version should be installed. To fix this, remove duplicate entries and keep only one version specification per package."""
        
        else:
            return """This dependency conflict occurs due to incompatible version requirements between packages. Review the version constraints and ensure all packages are compatible with each other. Consider updating to compatible versions or using a dependency resolver."""
    
    def _extract_why(self, explanation: str, conflict: Dict) -> str:
        """Extract the 'why it happens' part from explanation."""
        # Simple extraction - look for sentences explaining the reason
        sentences = explanation.split('.')
        why_sentences = [s.strip() for s in sentences if any(word in s.lower() for word in ['because', 'due to', 'requires', 'needs', 'since'])]
        return '. '.join(why_sentences[:2]) + '.' if why_sentences else "Version constraints are incompatible."
    
    def _extract_fix(self, explanation: str, conflict: Dict) -> str:
        """Extract the 'how to fix' part from explanation."""
        # Simple extraction - look for fix suggestions
        sentences = explanation.split('.')
        fix_sentences = [s.strip() for s in sentences if any(word in s.lower() for word in ['upgrade', 'downgrade', 'fix', 'change', 'update', 'remove'])]
        return '. '.join(fix_sentences[:2]) + '.' if fix_sentences else "Adjust version constraints to compatible versions."


def process_dependencies(
    library_list: str,
    requirements_text: str,
    uploaded_file,
    python_version: str,
    device: str,
    os_type: str,
    mode: str,
    resolution_strategy: str,
    use_llm_explanations: bool = True,
    use_ml_prediction: bool = True,
    use_ml_spellcheck: bool = True,
    show_ml_details: bool = False
) -> Tuple[str, str, str]:
    """Main processing function for Gradio interface."""
    
    # Collect dependencies from all sources
    all_dependencies = []
    
    # Parse library list
    if library_list:
        parser = DependencyParser()
        deps = parser.parse_library_list(library_list)
        all_dependencies.extend(deps)
    
    # Parse requirements text
    if requirements_text:
        parser = DependencyParser()
        deps = parser.parse_requirements_text(requirements_text)
        all_dependencies.extend(deps)
    
    # Parse uploaded file
    if uploaded_file:
        try:
            # Handle both string paths and file objects (Gradio 6.x compatibility)
            if isinstance(uploaded_file, str):
                file_path = uploaded_file
            else:
                # If it's a file object, get the path
                file_path = uploaded_file.name if hasattr(uploaded_file, 'name') else str(uploaded_file)
            
            with open(file_path, 'r') as f:
                content = f.read()
            parser = DependencyParser()
            deps = parser.parse_requirements_text(content)
            all_dependencies.extend(deps)
        except Exception as e:
            return f"Error reading file: {str(e)}", "", ""
    
    if not all_dependencies:
        return "Please provide at least one input: library list, requirements text, or uploaded file.", "", ""
    
    catalog_validator = CatalogValidator(use_ml=use_ml_spellcheck and ML_AVAILABLE)
    # Auto-correct spelling mistakes in package names
    all_dependencies, catalog_warnings = catalog_validator.check_and_correct_packages(all_dependencies, auto_correct=True)

    # ML-based conflict prediction (pre-analysis)
    ml_conflict_prediction = None
    ml_confidence = 0.0
    ml_details = ""
    if use_ml_prediction and ML_AVAILABLE:
        try:
            predictor = ConflictPredictor()
            requirements_text_for_ml = '\n'.join([d['original'] for d in all_dependencies])
            has_conflict, confidence = predictor.predict(requirements_text_for_ml)
            ml_conflict_prediction = has_conflict
            ml_confidence = confidence
            
            # Build ML details output
            ml_details = f"""
### ML Model Details

**Conflict Prediction Model:**
- Prediction: {"Conflict Detected" if has_conflict else "No Conflict"}
- Confidence: {confidence:.2%}
- Model Type: Random Forest Classifier
- Features Analyzed: Package presence, version specificity, conflict patterns

"""
            if show_ml_details:
                # Get feature importance or additional details
                ml_details += f"""
**Raw Prediction:**
- Has Conflict: {has_conflict}
- Confidence Score: {confidence:.4f}
- Probability Distribution: Conflict={confidence:.2%}, No Conflict={1-confidence:.2%}

"""
            
            if has_conflict and confidence > 0.7:
                catalog_warnings.append(
                    f"ML Prediction: High probability ({confidence:.1%}) of conflicts detected"
                )
        except Exception as e:
            print(f"ML prediction error: {e}")
            ml_details = f"ML Prediction Error: {str(e)}"
    elif use_ml_prediction and not ML_AVAILABLE:
        ml_details = "ML models not available. Train models using `train_conflict_model.py` to enable this feature."

    # Build dependency graph
    resolver = DependencyResolver(python_version=python_version, platform=os_type, device=device)
    deep_mode = (mode == "Deep (with transitive dependencies)")
    graph = resolver.build_dependency_graph(all_dependencies, deep_mode=deep_mode)
    
    # Check compatibility
    is_compatible, issues = resolver.check_compatibility(graph)
    
    # Convert string issues to structured format for LLM explanations
    structured_issues = []
    for issue in issues:
        if isinstance(issue, str):
            # Parse the issue string to extract package names and type
            issue_dict = {
                'type': 'version_incompatibility',
                'message': issue,
                'severity': 'high',
                'details': {}
            }
            
            # Extract package names from known patterns
            packages = []
            issue_lower = issue.lower()
            
            # Check for specific known conflicts
            if 'pytorch-lightning' in issue_lower and 'torch' in issue_lower:
                packages = ['pytorch-lightning', 'torch']
                issue_dict['type'] = 'version_incompatibility'
                # Extract version details
                for dep in all_dependencies:
                    if dep['package'] in packages:
                        issue_dict['details'][dep['package']] = dep.get('specifier', '')
            elif 'fastapi' in issue_lower and 'pydantic' in issue_lower:
                packages = ['fastapi', 'pydantic']
                issue_dict['type'] = 'version_incompatibility'
                for dep in all_dependencies:
                    if dep['package'] in packages:
                        issue_dict['details'][dep['package']] = dep.get('specifier', '')
            elif 'tensorflow' in issue_lower and 'keras' in issue_lower:
                packages = ['tensorflow', 'keras']
                issue_dict['type'] = 'version_incompatibility'
                for dep in all_dependencies:
                    if dep['package'] in packages:
                        issue_dict['details'][dep['package']] = dep.get('specifier', '')
            elif 'conflict in' in issue_lower:
                # Duplicate package conflict
                pkg = issue.split('Conflict in')[1].split(':')[0].strip()
                packages = [pkg]
                issue_dict['type'] = 'duplicate'
                issue_dict['package'] = pkg
            else:
                # Generic: try to find packages mentioned in the issue
                for dep in all_dependencies:
                    if dep['package'] in issue_lower:
                        packages.append(dep['package'])
            
            if packages:
                issue_dict['packages'] = packages
            else:
                issue_dict['package'] = 'unknown'
                issue_dict['packages'] = []
            
            structured_issues.append(issue_dict)
        else:
            structured_issues.append(issue)
    
    # Generate LLM explanations if enabled
    explanations = []
    if use_llm_explanations and structured_issues:
        explanation_engine = ExplanationEngine(use_llm=use_llm_explanations)
        for issue in structured_issues:
            try:
                explanation = explanation_engine.generate_explanation(issue, all_dependencies)
                explanations.append(explanation)
            except Exception as e:
                # If explanation generation fails, just use the issue message
                explanations.append({
                    'summary': issue.get('message', str(issue)),
                    'explanation': issue.get('message', str(issue)),
                    'why_it_happens': 'Unable to generate explanation.',
                    'how_to_fix': 'Review version constraints.',
                    'packages_involved': issue.get('packages', []),
                    'severity': issue.get('severity', 'medium')
                })
    
    # Resolve dependencies
    resolved_text, resolver_warnings = resolver.resolve_dependencies(all_dependencies, resolution_strategy)
    warnings = catalog_warnings + resolver_warnings
    
    # Build output message
    output_parts = []
    output_parts.append("## Dependency Analysis Results\n\n")
    
    # Show ML prediction if available
    if ML_AVAILABLE and ml_conflict_prediction is not None:
        if ml_conflict_prediction:
            output_parts.append(f"### ML Prediction: Potential Conflicts Detected (Confidence: {ml_confidence:.1%})\n\n")
        else:
            output_parts.append(f"### ML Prediction: Low Conflict Risk (Confidence: {ml_confidence:.1%})\n\n")
    
    if issues:
        output_parts.append("### Compatibility Issues Found:\n")
        if explanations:
            # Show detailed LLM explanations
            for i, (issue, explanation) in enumerate(zip(issues, explanations), 1):
                output_parts.append(f"#### Issue #{i}: {explanation['summary']}\n\n")
                output_parts.append(f"**Explanation:**\n{explanation['explanation']}\n\n")
                output_parts.append(f"**Why this happens:**\n{explanation['why_it_happens']}\n\n")
                output_parts.append(f"**How to fix:**\n{explanation['how_to_fix']}\n\n")
                output_parts.append("---\n\n")
        else:
            # Fallback to simple list
            for issue in issues:
                output_parts.append(f"- {issue}\n")
        output_parts.append("\n")
    
    # Separate corrections from other warnings
    corrections = [w for w in warnings if "Auto-corrected" in w or "→" in w]
    other_warnings = [w for w in warnings if w not in corrections]
    
    if corrections:
        output_parts.append("### Spelling Corrections:\n")
        for correction in corrections:
            output_parts.append(f"- {correction}\n")
        output_parts.append("\n")
    
    if other_warnings:
        output_parts.append("### Warnings:\n")
        for warning in other_warnings:
            output_parts.append(f"- {warning}\n")
        output_parts.append("\n")
    
    if is_compatible and not issues:
        output_parts.append("### No compatibility issues detected!\n\n")
    
    output_parts.append(f"### Resolved Requirements ({len(all_dependencies)} packages):\n")
    output_parts.append("```\n")
    output_parts.append(resolved_text)
    output_parts.append("\n```\n")
    
    # Add ML details if requested
    if show_ml_details and ml_details:
        output_parts.append(ml_details)
    
    return ''.join(output_parts), resolved_text, ml_details


# Gradio Interface
def create_interface():
    """Create and return the Gradio interface."""
    import gradio as gr
    
    with gr.Blocks(title="Python Dependency Compatibility Board") as app:
        gr.Markdown("""
        # Python Dependency Compatibility Board
        
        Analyze and resolve Python package dependencies with **AI-powered explanations** and **ML-based conflict prediction**.
        
        ## Key Features
        
        | Feature | Status | Description |
        |---------|--------|-------------|
        | **LLM Reasoning** | Active | AI-powered natural language explanations for conflicts |
        | **ML Conflict Prediction** | {"Available" if ML_AVAILABLE else "Not Loaded"} | Machine learning model predicts conflicts before analysis |
        | **Embedding-Based Spell Check** | {"Available" if ML_AVAILABLE else "Not Loaded"} | Semantic similarity matching for package names |
        | **Auto-Correction** | Active | Automatically fixes spelling mistakes in package names |
        | **Dependency Resolution** | Active | Resolves conflicts using pip's resolver |
        
        """)
        
        with gr.Row():
            with gr.Column(scale=1):
                gr.Markdown("### Input Methods")
                
                library_input = gr.Textbox(
                    label="Library Names (one per line)",
                    placeholder="pandas\ntorch\nlangchain\nfastapi",
                    lines=5,
                    info="Enter package names, one per line"
                )
                
                requirements_input = gr.Textbox(
                    label="Requirements.txt Content",
                    placeholder="pandas==2.0.3\ntorch>=2.0.0\nlangchain==0.1.0",
                    lines=10,
                    info="Paste your requirements.txt content here"
                )
                
                file_upload = gr.File(
                    label="Upload requirements.txt",
                    file_types=[".txt"]
                )
            
            with gr.Column(scale=1):
                gr.Markdown("### Environment Settings")
                
                python_version = gr.Dropdown(
                    choices=["3.8", "3.9", "3.10", "3.11", "3.12"],
                    value="3.10",
                    label="Python Version",
                    info="Target Python version"
                )
                
                device = gr.Dropdown(
                    choices=["CPU only", "NVIDIA GPU (CUDA)", "Apple Silicon (MPS)", "Custom / other"],
                    value="CPU only",
                    label="Device",
                    info="Target device/platform"
                )
                
                os_type = gr.Dropdown(
                    choices=["Any / generic", "Linux (x86_64)", "Windows (x86_64)", "MacOS (Intel)", "MacOS (Apple Silicon)"],
                    value="Any / generic",
                    label="Operating System",
                    info="Target operating system"
                )
                
                mode = gr.Radio(
                    choices=["Quick (top-level only)", "Deep (with transitive dependencies)"],
                    value="Quick (top-level only)",
                    label="Analysis Mode",
                    info="Quick mode is faster, Deep mode includes all dependencies"
                )
                
                resolution_strategy = gr.Dropdown(
                    choices=["latest_compatible", "stable/pinned", "keep_existing_pins", "minimal_changes"],
                    value="latest_compatible",
                    label="Resolution Strategy",
                    info="How to resolve version conflicts"
                )
                
                gr.Markdown("---")
                gr.Markdown("### AI & ML Features")
                
                use_llm = gr.Checkbox(
                    label="**LLM Reasoning** - AI Explanations",
                    value=True,
                    info="Generate intelligent, natural language explanations for conflicts using LLM"
                )
                
                use_ml_prediction = gr.Checkbox(
                    label="**ML Conflict Prediction**",
                    value=True,
                    info=f"{'Model available - Predicts conflicts before detailed analysis' if ML_AVAILABLE else 'Model not loaded - Train models to enable'}"
                )
                
                use_ml_spellcheck = gr.Checkbox(
                    label="**ML Spell Check** (Embedding-based)",
                    value=True,
                    info=f"{'Model available - Uses semantic similarity for better corrections' if ML_AVAILABLE else 'Model not loaded - Train models to enable'}"
                )
                
                show_ml_details = gr.Checkbox(
                    label="Show ML Model Details",
                    value=False,
                    info="Display raw ML predictions and confidence scores"
                )
                
                process_btn = gr.Button("Analyze & Resolve Dependencies", variant="primary", size="lg")
        
        with gr.Row():
            output_display = gr.Markdown(
                label="Analysis Results",
                value="Results will appear here after processing..."
            )
        
        with gr.Row():
            with gr.Column(scale=2):
                resolved_output = gr.Textbox(
                    label="Resolved requirements.txt",
                    lines=15,
                    info="Copy this content to use as your requirements.txt file"
                )
                
                download_btn = gr.File(
                    label="Download requirements.txt",
                    value=None,
                    visible=True
                )
            
            with gr.Column(scale=1):
                ml_output = gr.Markdown(
                    label="ML Model Output",
                    value="ML predictions will appear here when enabled...",
                    visible=True
                )
        
        def process_and_download(*args):
            # Extract all arguments
            result_text, resolved_text, ml_details = process_dependencies(*args)
            
            # Create a temporary file for download
            temp_file = None
            if resolved_text and resolved_text.strip():
                try:
                    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
                        f.write(resolved_text)
                        temp_file = f.name
                except Exception as e:
                    print(f"Error creating download file: {e}")
            
            # Format ML output
            ml_output_text = ml_details if ml_details else "ML features disabled or models not available."
            
            return result_text, resolved_text, temp_file if temp_file else None, ml_output_text
        
        process_btn.click(
            fn=process_and_download,
            inputs=[library_input, requirements_input, file_upload, python_version, device, os_type, mode, resolution_strategy, use_llm, use_ml_prediction, use_ml_spellcheck, show_ml_details],
            outputs=[output_display, resolved_output, download_btn, ml_output]
        )
        
        gr.Markdown("""
        ---
        ### How to Use
        
        1. **Input your dependencies** using any of the three methods (or combine them)
        2. **Configure your environment** (Python version, device, OS)
        3. **Choose analysis mode**: Quick for fast results, Deep for complete dependency tree
        4. **Select resolution strategy**: How to handle version conflicts
        5. **Click "Analyze & Resolve Dependencies"**
        6. **Review the results** and download the resolved requirements.txt
        
        ### Features
        
        - Parse multiple input formats
        - Detect version conflicts
        - Check compatibility across dependency graph
        - Resolve dependencies using pip
        - Generate clean, pip-compatible requirements.txt
        - Environment-aware (Python version, platform, device)
        """)
    
    return app


if __name__ == "__main__":
    app = create_interface()
    # For Hugging Face Spaces, use default launch settings
    # For local development, you can customize
    app.launch()