mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-08 02:14:08 +08:00
feat: Add pycli bash wrapper with hierarchical vector database support
- Create unified bash wrapper (pycli) for Python CLI tools - Implement hierarchical vector database with smart parent discovery - Add comprehensive installation script with auto-configuration - Remove redundant analyzer.py and api_indexer.py files - Enhance Python scripts with environment variable support - Update documentation to focus on pycli unified interface Key Features: - Automatic parent directory vector DB discovery - No redundant vectorization in subdirectories - Central vector database storage in ~/.claude/vector_db - Configurable Python interpreter paths - One-command installation and setup 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
@@ -1,305 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Unified Path-Aware Analyzer
|
||||
Main entry point for the refactored analyzer system.
|
||||
Provides a clean, simple API for intelligent file analysis.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import argparse
|
||||
import logging
|
||||
import json
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Any
|
||||
|
||||
# Add current directory to path for imports
|
||||
sys.path.insert(0, str(Path(__file__).parent))
|
||||
|
||||
from core.config import get_config
|
||||
from core.file_indexer import FileIndexer, IndexStats
|
||||
from core.context_analyzer import ContextAnalyzer, AnalysisResult
|
||||
from core.path_matcher import PathMatcher, PathMatchingResult
|
||||
from core.embedding_manager import EmbeddingManager
|
||||
from utils.colors import Colors
|
||||
|
||||
|
||||
class Analyzer:
|
||||
"""Main analyzer class with simplified API."""
|
||||
|
||||
def __init__(self, config_path: Optional[str] = None, root_path: str = "."):
|
||||
self.root_path = Path(root_path).resolve()
|
||||
self.config = get_config(config_path)
|
||||
|
||||
# Setup logging
|
||||
logging.basicConfig(
|
||||
level=getattr(logging, self.config.get('logging.level', 'INFO')),
|
||||
format=self.config.get('logging.format', '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
)
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
# Initialize core components
|
||||
self.indexer = FileIndexer(self.config, str(self.root_path))
|
||||
self.context_analyzer = ContextAnalyzer(self.config)
|
||||
self.path_matcher = PathMatcher(self.config)
|
||||
|
||||
# Initialize embedding manager if enabled
|
||||
self.embedding_manager = None
|
||||
if self.config.is_embedding_enabled():
|
||||
try:
|
||||
self.embedding_manager = EmbeddingManager(self.config)
|
||||
except ImportError:
|
||||
self.logger.warning("Embedding dependencies not available. Install sentence-transformers for enhanced functionality.")
|
||||
|
||||
def build_index(self) -> IndexStats:
|
||||
"""Build or update the file index."""
|
||||
print(Colors.yellow("Building file index..."))
|
||||
start_time = time.time()
|
||||
|
||||
self.indexer.build_index()
|
||||
stats = self.indexer.get_stats()
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
if stats:
|
||||
print(Colors.green(f"Index built: {stats.total_files} files, ~{stats.total_tokens:,} tokens ({elapsed:.2f}s)"))
|
||||
else:
|
||||
print(Colors.green(f"Index built successfully ({elapsed:.2f}s)"))
|
||||
|
||||
return stats
|
||||
|
||||
def analyze(self, prompt: str, mode: str = "auto", patterns: Optional[List[str]] = None,
|
||||
token_limit: Optional[int] = None, use_embeddings: Optional[bool] = None) -> Dict[str, Any]:
|
||||
"""Analyze and return relevant file paths for a given prompt."""
|
||||
|
||||
print(Colors.yellow("Analyzing project and prompt..."))
|
||||
start_time = time.time()
|
||||
|
||||
# Load or build index
|
||||
index = self.indexer.load_index()
|
||||
if not index:
|
||||
self.build_index()
|
||||
index = self.indexer.load_index()
|
||||
|
||||
stats = self.indexer.get_stats()
|
||||
print(Colors.cyan(f"Project stats: ~{stats.total_tokens:,} tokens across {stats.total_files} files"))
|
||||
print(Colors.cyan(f"Categories: {', '.join(f'{k}: {v}' for k, v in stats.categories.items())}"))
|
||||
|
||||
# Determine project size
|
||||
project_size = self._classify_project_size(stats.total_tokens)
|
||||
print(Colors.cyan(f"Project size: {project_size}"))
|
||||
|
||||
# Analyze prompt context
|
||||
print(Colors.yellow("Analyzing prompt context..."))
|
||||
context_result = self.context_analyzer.analyze(prompt)
|
||||
|
||||
print(Colors.cyan(f"Identified: {len(context_result.domains)} domains, {len(context_result.languages)} languages"))
|
||||
if context_result.domains:
|
||||
print(Colors.cyan(f"Top domains: {', '.join(context_result.domains[:3])}"))
|
||||
|
||||
# Determine if we should use embeddings
|
||||
should_use_embeddings = use_embeddings
|
||||
if should_use_embeddings is None:
|
||||
should_use_embeddings = (
|
||||
self.embedding_manager is not None and
|
||||
self.config.is_embedding_enabled() and
|
||||
len(context_result.keywords) < 5 # Use embeddings for vague queries
|
||||
)
|
||||
|
||||
similar_files = []
|
||||
if should_use_embeddings and self.embedding_manager:
|
||||
print(Colors.yellow("Using semantic similarity search..."))
|
||||
# Update embeddings if needed
|
||||
if not self.embedding_manager.embeddings_exist():
|
||||
print(Colors.yellow("Building embeddings (first run)..."))
|
||||
self.embedding_manager.update_embeddings(index)
|
||||
|
||||
similar_files = self.embedding_manager.find_similar_files(prompt, index)
|
||||
print(Colors.cyan(f"Found {len(similar_files)} semantically similar files"))
|
||||
|
||||
# Match files to context
|
||||
print(Colors.yellow("Matching files to context..."))
|
||||
matching_result = self.path_matcher.match_files(
|
||||
index,
|
||||
context_result,
|
||||
token_limit=token_limit,
|
||||
explicit_patterns=patterns
|
||||
)
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
|
||||
print(Colors.green(f"Analysis complete: {len(matching_result.matched_files)} files, ~{matching_result.total_tokens:,} tokens"))
|
||||
print(Colors.cyan(f"Confidence: {matching_result.confidence_score:.2f}"))
|
||||
print(Colors.cyan(f"Execution time: {elapsed:.2f}s"))
|
||||
|
||||
return {
|
||||
'files': [match.file_info.relative_path for match in matching_result.matched_files],
|
||||
'total_tokens': matching_result.total_tokens,
|
||||
'confidence': matching_result.confidence_score,
|
||||
'context': {
|
||||
'domains': context_result.domains,
|
||||
'languages': context_result.languages,
|
||||
'keywords': context_result.keywords
|
||||
},
|
||||
'stats': {
|
||||
'project_size': project_size,
|
||||
'total_files': stats.total_files,
|
||||
'analysis_time': elapsed,
|
||||
'embeddings_used': should_use_embeddings
|
||||
}
|
||||
}
|
||||
|
||||
def generate_command(self, prompt: str, tool: str = "gemini", **kwargs) -> str:
|
||||
"""Generate a command for external tools (gemini/codex)."""
|
||||
analysis_result = self.analyze(prompt, **kwargs)
|
||||
|
||||
# Format file patterns
|
||||
file_patterns = " ".join(f"@{{{file}}}" for file in analysis_result['files'])
|
||||
|
||||
if tool == "gemini":
|
||||
if len(analysis_result['files']) > 50: # Too many files for individual patterns
|
||||
return f'gemini --all-files -p "{prompt}"'
|
||||
else:
|
||||
return f'gemini -p "{file_patterns} {prompt}"'
|
||||
|
||||
elif tool == "codex":
|
||||
workspace_flag = "-s workspace-write" if analysis_result['total_tokens'] > 100000 else "-s danger-full-access"
|
||||
return f'codex {workspace_flag} --full-auto exec "{file_patterns} {prompt}"'
|
||||
|
||||
else:
|
||||
raise ValueError(f"Unsupported tool: {tool}")
|
||||
|
||||
def _classify_project_size(self, tokens: int) -> str:
|
||||
"""Classify project size based on token count."""
|
||||
small_limit = self.config.get('token_limits.small_project', 500000)
|
||||
medium_limit = self.config.get('token_limits.medium_project', 2000000)
|
||||
|
||||
if tokens < small_limit:
|
||||
return "small"
|
||||
elif tokens < medium_limit:
|
||||
return "medium"
|
||||
else:
|
||||
return "large"
|
||||
|
||||
def get_project_stats(self) -> Dict[str, Any]:
|
||||
"""Get comprehensive project statistics."""
|
||||
stats = self.indexer.get_stats()
|
||||
embedding_stats = {}
|
||||
|
||||
if self.embedding_manager:
|
||||
embedding_stats = {
|
||||
'embeddings_exist': self.embedding_manager.embeddings_exist(),
|
||||
'embedding_count': len(self.embedding_manager.load_embeddings()) if self.embedding_manager.embeddings_exist() else 0
|
||||
}
|
||||
|
||||
return {
|
||||
'files': stats.total_files,
|
||||
'tokens': stats.total_tokens,
|
||||
'size_bytes': stats.total_size,
|
||||
'categories': stats.categories,
|
||||
'project_size': self._classify_project_size(stats.total_tokens),
|
||||
'last_updated': stats.last_updated,
|
||||
'embeddings': embedding_stats,
|
||||
'config': {
|
||||
'cache_dir': self.config.get_cache_dir(),
|
||||
'embedding_enabled': self.config.is_embedding_enabled(),
|
||||
'exclude_patterns_count': len(self.config.get_exclude_patterns())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
def main():
|
||||
"""CLI entry point."""
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Path-Aware Analyzer - Intelligent file pattern detection",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog="""
|
||||
Examples:
|
||||
python analyzer.py "analyze authentication flow"
|
||||
python analyzer.py "fix database connection" --patterns "src/**/*.py"
|
||||
python analyzer.py "review API endpoints" --tool gemini
|
||||
python analyzer.py --stats
|
||||
"""
|
||||
)
|
||||
|
||||
parser.add_argument('prompt', nargs='?', help='Analysis prompt or task description')
|
||||
parser.add_argument('--patterns', nargs='*', help='Explicit file patterns to include')
|
||||
parser.add_argument('--tool', choices=['gemini', 'codex'], help='Generate command for specific tool')
|
||||
parser.add_argument('--output', choices=['patterns', 'json'], default='patterns', help='Output format')
|
||||
parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
|
||||
parser.add_argument('--stats', action='store_true', help='Show project statistics and exit')
|
||||
parser.add_argument('--build-index', action='store_true', help='Build file index and exit')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# Create analyzer with default values
|
||||
analyzer = Analyzer(config_path=None, root_path=".")
|
||||
|
||||
# Handle special commands
|
||||
if args.build_index:
|
||||
analyzer.build_index()
|
||||
return
|
||||
|
||||
if args.stats:
|
||||
stats = analyzer.get_project_stats()
|
||||
if args.output == 'json':
|
||||
print(json.dumps(stats, indent=2, default=str))
|
||||
else:
|
||||
print(f"Total files: {stats['files']}")
|
||||
print(f"Total tokens: {stats['tokens']:,}")
|
||||
print(f"Categories: {stats['categories']}")
|
||||
if 'embeddings' in stats:
|
||||
print(f"Embeddings: {stats['embeddings']['embedding_count']}")
|
||||
return
|
||||
|
||||
# Require prompt for analysis
|
||||
if not args.prompt:
|
||||
parser.error("Analysis prompt is required unless using --build-index or --stats")
|
||||
|
||||
# Perform analysis
|
||||
try:
|
||||
result = analyzer.analyze(
|
||||
args.prompt,
|
||||
patterns=args.patterns,
|
||||
use_embeddings=False # Disable embeddings by default for simplicity
|
||||
)
|
||||
|
||||
# Generate output
|
||||
if args.tool:
|
||||
# Generate command using already computed result
|
||||
file_patterns = " ".join(f"@{{{file}}}" for file in result['files'])
|
||||
if args.tool == "gemini":
|
||||
if len(result['files']) > 50:
|
||||
command = f'gemini --all-files -p "{args.prompt}"'
|
||||
else:
|
||||
command = f'gemini -p "{file_patterns} {args.prompt}"'
|
||||
elif args.tool == "codex":
|
||||
workspace_flag = "-s workspace-write" if result['total_tokens'] > 100000 else "-s danger-full-access"
|
||||
command = f'codex {workspace_flag} --full-auto exec "{file_patterns} {args.prompt}"'
|
||||
print(command)
|
||||
elif args.output == 'json':
|
||||
print(json.dumps(result, indent=2, default=str))
|
||||
else: # patterns output (default)
|
||||
for file_path in result['files']:
|
||||
print(f"@{{{file_path}}}")
|
||||
|
||||
# Show verbose details
|
||||
if args.verbose:
|
||||
print(f"\n# Analysis Details:")
|
||||
print(f"# Matched files: {len(result['files'])}")
|
||||
print(f"# Total tokens: {result['total_tokens']:,}")
|
||||
print(f"# Confidence: {result['confidence']:.2f}")
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print(Colors.warning("\nAnalysis interrupted by user"))
|
||||
sys.exit(1)
|
||||
except Exception as e:
|
||||
print(Colors.error(f"Analysis failed: {e}"))
|
||||
if args.verbose:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,141 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
API Documentation Indexer
|
||||
Parses Markdown documentation to create a searchable index of classes and methods.
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
import json
|
||||
import logging
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any
|
||||
|
||||
from core.file_indexer import FileIndexer
|
||||
|
||||
class ApiIndexer:
|
||||
def __init__(self, config: Dict, root_path: str = "."):
|
||||
self.config = config
|
||||
self.root_path = Path(root_path).resolve()
|
||||
self.file_indexer = FileIndexer(config, root_path)
|
||||
self.api_index_file = self.file_indexer.cache_dir / "api_index.json"
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
def build_index(self):
|
||||
"""Builds the API index from Markdown files."""
|
||||
self.logger.info("Building API index...")
|
||||
file_index = self.file_indexer.load_index()
|
||||
if not file_index:
|
||||
self.logger.info("File index not found, building it first.")
|
||||
self.file_indexer.build_index()
|
||||
file_index = self.file_indexer.load_index()
|
||||
|
||||
api_index = {}
|
||||
for file_info in file_index.values():
|
||||
if file_info.extension == ".md":
|
||||
self.logger.debug(f"Parsing {file_info.path}")
|
||||
try:
|
||||
with open(file_info.path, "r", encoding="utf-8") as f:
|
||||
content = f.read()
|
||||
self._parse_markdown(content, file_info.relative_path, api_index)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error parsing {file_info.path}: {e}")
|
||||
|
||||
self._save_index(api_index)
|
||||
self.logger.info(f"API index built with {len(api_index)} classes.")
|
||||
|
||||
def _parse_markdown(self, content: str, file_path: str, api_index: Dict):
|
||||
"""Parses a single Markdown file for class and method info."""
|
||||
class_name_match = re.search(r"^#\s+([A-Za-z0-9_]+)", content)
|
||||
if not class_name_match:
|
||||
return
|
||||
|
||||
class_name = class_name_match.group(1)
|
||||
api_index[class_name] = {
|
||||
"file_path": file_path,
|
||||
"description": "",
|
||||
"methods": {}
|
||||
}
|
||||
|
||||
# Simple description extraction
|
||||
desc_match = re.search(r"\*\*Description:\*\*\s*(.+)", content)
|
||||
if desc_match:
|
||||
api_index[class_name]["description"] = desc_match.group(1).strip()
|
||||
|
||||
# Method extraction
|
||||
method_sections = re.split(r"###\s+", content)[1:]
|
||||
for i, section in enumerate(method_sections):
|
||||
method_signature_match = re.search(r"`(.+?)`", section)
|
||||
if not method_signature_match:
|
||||
continue
|
||||
|
||||
signature = method_signature_match.group(1)
|
||||
method_name_match = re.search(r"([A-Za-z0-9_]+)\(“, signature)
|
||||
if not method_name_match:
|
||||
continue
|
||||
|
||||
method_name = method_name_match.group(1)
|
||||
|
||||
method_description = ""
|
||||
method_desc_match = re.search(r"\*\*Description:\*\*\s*(.+)", section)
|
||||
if method_desc_match:
|
||||
method_description = method_desc_match.group(1).strip()
|
||||
|
||||
# A simple way to get a line number approximation
|
||||
line_number = content.count("\n", 0, content.find(f"### `{signature}`")) + 1
|
||||
|
||||
api_index[class_name]["methods"Показать больше] = {
|
||||
"signature": signature,
|
||||
"description": method_description,
|
||||
"line_number": line_number
|
||||
}
|
||||
|
||||
def _save_index(self, api_index: Dict):
|
||||
"""Saves the API index to a file."""
|
||||
try:
|
||||
with open(self.api_index_file, "w", encoding="utf-8") as f:
|
||||
json.dump(api_index, f, indent=2)
|
||||
except IOError as e:
|
||||
self.logger.error(f"Could not save API index: {e}")
|
||||
|
||||
def search(self, class_name: str, method_name: str = None) -> Any:
|
||||
"""Searches the API index for a class or method."""
|
||||
if not self.api_index_file.exists():
|
||||
self.build_index()
|
||||
|
||||
with open(self.api_index_file, "r", encoding="utf-8") as f:
|
||||
api_index = json.load(f)
|
||||
|
||||
if class_name not in api_index:
|
||||
return None
|
||||
|
||||
if method_name:
|
||||
return api_index[class_name]["methods"].get(method_name)
|
||||
else:
|
||||
return api_index[class_name]
|
||||
|
||||
if __name__ == "__main__":
|
||||
from core.config import get_config
|
||||
import argparse
|
||||
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
|
||||
parser = argparse.ArgumentParser(description="API Documentation Indexer.")
|
||||
parser.add_argument("--build", action="store_true", help="Build the API index.")
|
||||
parser.add_argument("--search_class", help="Search for a class.")
|
||||
parser.add_argument("--search_method", help="Search for a method within a class (requires --search_class).")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
config = get_config()
|
||||
api_indexer = ApiIndexer(config.to_dict())
|
||||
|
||||
if args.build:
|
||||
api_indexer.build_index()
|
||||
|
||||
if args.search_class:
|
||||
result = api_indexer.search(args.search_class, args.search_method)
|
||||
if result:
|
||||
print(json.dumps(result, indent=2))
|
||||
else:
|
||||
print("Not found.")
|
||||
276
.claude/python_script/cache/file_index.json
vendored
276
.claude/python_script/cache/file_index.json
vendored
@@ -1,276 +0,0 @@
|
||||
{
|
||||
"stats": {
|
||||
"total_files": 26,
|
||||
"total_tokens": 56126,
|
||||
"total_size": 246519,
|
||||
"categories": {
|
||||
"code": 21,
|
||||
"config": 3,
|
||||
"docs": 1,
|
||||
"other": 1
|
||||
},
|
||||
"last_updated": 1758177270.9103189
|
||||
},
|
||||
"files": {
|
||||
"analyzer.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\analyzer.py",
|
||||
"relative_path": "analyzer.py",
|
||||
"size": 12595,
|
||||
"modified_time": 1758175179.730658,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 3072,
|
||||
"content_hash": "3fb090745b5080e0731e7ef3fc94029d"
|
||||
},
|
||||
"cli.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\cli.py",
|
||||
"relative_path": "cli.py",
|
||||
"size": 8329,
|
||||
"modified_time": 1758177193.3710027,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 2030,
|
||||
"content_hash": "b9f0b5d6a154cf51c8665b2344c9faf8"
|
||||
},
|
||||
"config.yaml": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\config.yaml",
|
||||
"relative_path": "config.yaml",
|
||||
"size": 4317,
|
||||
"modified_time": 1758163450.6223683,
|
||||
"extension": ".yaml",
|
||||
"category": "config",
|
||||
"estimated_tokens": 1040,
|
||||
"content_hash": "b431b73dfa86ff83145468bbf4422a79"
|
||||
},
|
||||
"indexer.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\indexer.py",
|
||||
"relative_path": "indexer.py",
|
||||
"size": 7776,
|
||||
"modified_time": 1758177151.2160237,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 1893,
|
||||
"content_hash": "f88b5e5bffce26f3170974df2906aac3"
|
||||
},
|
||||
"install.sh": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\install.sh",
|
||||
"relative_path": "install.sh",
|
||||
"size": 5236,
|
||||
"modified_time": 1758161898.317552,
|
||||
"extension": ".sh",
|
||||
"category": "code",
|
||||
"estimated_tokens": 1262,
|
||||
"content_hash": "cc3a9121a0b8281457270f30ad76f5f6"
|
||||
},
|
||||
"requirements.txt": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\requirements.txt",
|
||||
"relative_path": "requirements.txt",
|
||||
"size": 495,
|
||||
"modified_time": 1758164967.7707567,
|
||||
"extension": ".txt",
|
||||
"category": "docs",
|
||||
"estimated_tokens": 118,
|
||||
"content_hash": "aea2ba14dfa7b37b1dde5518de87d956"
|
||||
},
|
||||
"setup.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\setup.py",
|
||||
"relative_path": "setup.py",
|
||||
"size": 2860,
|
||||
"modified_time": 1758177212.9095325,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 692,
|
||||
"content_hash": "609abf8b9c84a09f6a59d5815eb90bc5"
|
||||
},
|
||||
"__init__.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\__init__.py",
|
||||
"relative_path": "__init__.py",
|
||||
"size": 1065,
|
||||
"modified_time": 1758177224.8017242,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 257,
|
||||
"content_hash": "47368b235086fc0c75ba34a824c58506"
|
||||
},
|
||||
"cache\\embeddings.pkl": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\cache\\embeddings.pkl",
|
||||
"relative_path": "cache\\embeddings.pkl",
|
||||
"size": 35109,
|
||||
"modified_time": 1758175163.6754165,
|
||||
"extension": ".pkl",
|
||||
"category": "other",
|
||||
"estimated_tokens": 4713,
|
||||
"content_hash": "b8ed5c068acd5ed52ba10839701a5a24"
|
||||
},
|
||||
"cache\\embedding_index.json": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\cache\\embedding_index.json",
|
||||
"relative_path": "cache\\embedding_index.json",
|
||||
"size": 5589,
|
||||
"modified_time": 1758175163.6764157,
|
||||
"extension": ".json",
|
||||
"category": "config",
|
||||
"estimated_tokens": 1358,
|
||||
"content_hash": "5c2ba41b1b69ce19d2fc3b5854f6ee53"
|
||||
},
|
||||
"cache\\file_index.json": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\cache\\file_index.json",
|
||||
"relative_path": "cache\\file_index.json",
|
||||
"size": 12164,
|
||||
"modified_time": 1758165699.0883024,
|
||||
"extension": ".json",
|
||||
"category": "config",
|
||||
"estimated_tokens": 2957,
|
||||
"content_hash": "73563db28a2808aa28544c0275b97f94"
|
||||
},
|
||||
"core\\config.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\config.py",
|
||||
"relative_path": "core\\config.py",
|
||||
"size": 12266,
|
||||
"modified_time": 1758164531.5934324,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 2985,
|
||||
"content_hash": "d85aedc01a528b486d41acbd823181d7"
|
||||
},
|
||||
"core\\context_analyzer.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\context_analyzer.py",
|
||||
"relative_path": "core\\context_analyzer.py",
|
||||
"size": 15002,
|
||||
"modified_time": 1758164846.7665854,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 3661,
|
||||
"content_hash": "677903b5aaf3db13575ca1ca99ec7c16"
|
||||
},
|
||||
"core\\embedding_manager.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\embedding_manager.py",
|
||||
"relative_path": "core\\embedding_manager.py",
|
||||
"size": 17271,
|
||||
"modified_time": 1758166063.1635072,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 4204,
|
||||
"content_hash": "d8f52cb93140a46fe3d22d465ec01b22"
|
||||
},
|
||||
"core\\file_indexer.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\file_indexer.py",
|
||||
"relative_path": "core\\file_indexer.py",
|
||||
"size": 14484,
|
||||
"modified_time": 1758164612.5888917,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 3525,
|
||||
"content_hash": "1518d309108f3300417b65f6234241d1"
|
||||
},
|
||||
"core\\gitignore_parser.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\gitignore_parser.py",
|
||||
"relative_path": "core\\gitignore_parser.py",
|
||||
"size": 6757,
|
||||
"modified_time": 1758164472.643646,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 1644,
|
||||
"content_hash": "9cd97725576727080aaafd329d9ce2c4"
|
||||
},
|
||||
"core\\path_matcher.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\path_matcher.py",
|
||||
"relative_path": "core\\path_matcher.py",
|
||||
"size": 19568,
|
||||
"modified_time": 1758166045.8395746,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 4767,
|
||||
"content_hash": "f1dc44dc3ed67f100770aea40197623f"
|
||||
},
|
||||
"core\\__init__.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\core\\__init__.py",
|
||||
"relative_path": "core\\__init__.py",
|
||||
"size": 712,
|
||||
"modified_time": 1758164419.4437866,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 172,
|
||||
"content_hash": "b25991cb8d977021362f45e121e89de7"
|
||||
},
|
||||
"tools\\module_analyzer.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\tools\\module_analyzer.py",
|
||||
"relative_path": "tools\\module_analyzer.py",
|
||||
"size": 14273,
|
||||
"modified_time": 1758164687.488236,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 3476,
|
||||
"content_hash": "b958ec7ed264242f2bb30b1cca66b144"
|
||||
},
|
||||
"tools\\tech_stack.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\tools\\tech_stack.py",
|
||||
"relative_path": "tools\\tech_stack.py",
|
||||
"size": 7576,
|
||||
"modified_time": 1758164695.643722,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 1843,
|
||||
"content_hash": "f391a45d8254f0c4f4f789027dd69afc"
|
||||
},
|
||||
"tools\\workflow_updater.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\tools\\workflow_updater.py",
|
||||
"relative_path": "tools\\workflow_updater.py",
|
||||
"size": 9577,
|
||||
"modified_time": 1758164703.2230499,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 2334,
|
||||
"content_hash": "526edf0cfbe3c2041135eace9f89ef13"
|
||||
},
|
||||
"tools\\__init__.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\tools\\__init__.py",
|
||||
"relative_path": "tools\\__init__.py",
|
||||
"size": 329,
|
||||
"modified_time": 1758165927.9923615,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 79,
|
||||
"content_hash": "139aa450d7511347cc6799c471eac745"
|
||||
},
|
||||
"utils\\cache.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\utils\\cache.py",
|
||||
"relative_path": "utils\\cache.py",
|
||||
"size": 12067,
|
||||
"modified_time": 1758164781.2914226,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 2929,
|
||||
"content_hash": "39e49b731d601fafac74e96ed074e654"
|
||||
},
|
||||
"utils\\colors.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\utils\\colors.py",
|
||||
"relative_path": "utils\\colors.py",
|
||||
"size": 6959,
|
||||
"modified_time": 1758165650.9865932,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 1678,
|
||||
"content_hash": "8bb57134555d8fb07d2e351d4e100f0f"
|
||||
},
|
||||
"utils\\io_helpers.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\utils\\io_helpers.py",
|
||||
"relative_path": "utils\\io_helpers.py",
|
||||
"size": 13773,
|
||||
"modified_time": 1758164823.513003,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 3349,
|
||||
"content_hash": "aa54747c49319cc2c90c0544c668009a"
|
||||
},
|
||||
"utils\\__init__.py": {
|
||||
"path": "D:\\Claude_dms3\\.claude\\python_script\\utils\\__init__.py",
|
||||
"relative_path": "utils\\__init__.py",
|
||||
"size": 370,
|
||||
"modified_time": 1758164433.7142198,
|
||||
"extension": ".py",
|
||||
"category": "code",
|
||||
"estimated_tokens": 88,
|
||||
"content_hash": "62ec4a34f1643a23c79207061bdb8d49"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -66,12 +66,12 @@ file_extensions:
|
||||
# Embedding/RAG configuration
|
||||
embedding:
|
||||
enabled: true # Set to true to enable RAG features
|
||||
model: "codesage/codesage-large-v2" # CodeSage V2 for code embeddings
|
||||
model: "all-MiniLM-L6-v2" # Stable general-purpose embedding model
|
||||
cache_dir: "cache"
|
||||
similarity_threshold: 0.6 # Higher threshold for better code similarity
|
||||
max_context_length: 2048 # Increased for CodeSage V2 capabilities
|
||||
batch_size: 8 # Reduced for larger model
|
||||
trust_remote_code: true # Required for CodeSage V2
|
||||
max_context_length: 512 # Standard context length
|
||||
batch_size: 32 # Standard batch size
|
||||
trust_remote_code: false # Not required for standard models
|
||||
|
||||
# Context analysis settings
|
||||
context_analysis:
|
||||
|
||||
Reference in New Issue
Block a user