repotoire 0.1.3__tar.gz → 0.1.4__tar.gz

{repotoire-0.1.3 → repotoire-0.1.4}/PKG-INFO

@@ -1,10 +1,9 @@
 Metadata-Version: 2.4
 Name: repotoire
-Version: 0.1.3
+Version: 0.1.4
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
@@ -19,13 +18,12 @@ Requires-Dist: networkx>=3.2.0
 Requires-Dist: jinja2>=3.1.0
 Requires-Dist: detect-secrets>=1.4.0
 Requires-Dist: gitpython>=3.1.40
-Requires-Dist: neo4j-graphrag>=1.10.1
 Requires-Dist: fastapi>=0.121.3
 Requires-Dist: uvicorn>=0.38.0
 Requires-Dist: mcp>=1.22.0
 Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: clerk-backend-api>=4.2.0
-Requires-Dist: httpx>=0.27.0
+Requires-Dist: httpx[http2]>=0.27.0
 Requires-Dist: pyjwt[crypto]>=2.8.0
 Requires-Dist: cryptography>=41.0.0
 Requires-Dist: svix>=1.0.0
@@ -38,6 +36,7 @@ Requires-Dist: stripe>=7.0.0
 Requires-Dist: celery>=5.3.0
 Requires-Dist: redis>=5.0.0
 Requires-Dist: structlog>=24.0.0
+Requires-Dist: psutil>=5.9.0
 Requires-Dist: sentry-sdk[fastapi,celery,sqlalchemy]>=2.0.0
 Requires-Dist: resend>=0.5.0
 Requires-Dist: aioboto3>=13.0.0
@@ -49,12 +48,21 @@ Requires-Dist: uv-secure>=0.15.0
 Requires-Dist: datasets>=2.14.0
 Requires-Dist: sentence-transformers>=2.2.0
 Requires-Dist: accelerate>=0.26.0
+Requires-Dist: ruff>=0.1.0
 Requires-Dist: mypy>=1.7.0
 Requires-Dist: pylint>=3.0.0
 Requires-Dist: bandit>=1.7.0
 Requires-Dist: radon>=6.0.0
 Requires-Dist: vulture>=2.0.0
 Requires-Dist: semgrep>=1.0.0
+Requires-Dist: tree-sitter>=0.20.0 ; extra == 'all-languages'
+Requires-Dist: tree-sitter-python>=0.20.0 ; extra == 'all-languages'
+Requires-Dist: tree-sitter-javascript>=0.20.0 ; extra == 'all-languages'
+Requires-Dist: tree-sitter-typescript>=0.20.0 ; extra == 'all-languages'
+Requires-Dist: tree-sitter-java>=0.23.0 ; extra == 'all-languages'
+Requires-Dist: tree-sitter-go>=0.23.0 ; extra == 'all-languages'
+Requires-Dist: anthropic>=0.40.0 ; extra == 'anthropic'
+Requires-Dist: pyyaml>=6.0 ; extra == 'config'
 Requires-Dist: pytest>=7.4.0 ; extra == 'dev'
 Requires-Dist: pytest-cov>=4.1.0 ; extra == 'dev'
 Requires-Dist: pytest-xdist>=3.5.0 ; extra == 'dev'
@@ -63,63 +71,51 @@ Requires-Dist: pytest-asyncio>=0.23.0 ; extra == 'dev'
 Requires-Dist: pytest-timeout>=2.2.0 ; extra == 'dev'
 Requires-Dist: hypothesis>=6.100.0 ; extra == 'dev'
 Requires-Dist: factory-boy>=3.3.0 ; extra == 'dev'
-Requires-Dist: httpx>=0.27.0 ; extra == 'dev'
+Requires-Dist: aiosqlite>=0.20.0 ; extra == 'dev'
 Requires-Dist: black>=23.0.0 ; extra == 'dev'
 Requires-Dist: ruff>=0.1.0 ; extra == 'dev'
-Requires-Dist: mypy>=1.7.0 ; extra == 'dev'
 Requires-Dist: pyyaml>=6.0 ; extra == 'dev'
 Requires-Dist: tomli>=2.0.0 ; extra == 'dev'
 Requires-Dist: tenacity>=8.2.0 ; extra == 'dev'
-Requires-Dist: redis>=5.0.0 ; extra == 'dev'
-Requires-Dist: pyyaml>=6.0 ; extra == 'config'
-Requires-Dist: tomli>=2.0.0 ; python_full_version < '3.11' and extra == 'config'
-Requires-Dist: graphdatascience>=1.9.0 ; extra == 'gds'
-Requires-Dist: tree-sitter>=0.20.0 ; extra == 'all-languages'
-Requires-Dist: tree-sitter-python>=0.20.0 ; extra == 'all-languages'
-Requires-Dist: tree-sitter-javascript>=0.20.0 ; extra == 'all-languages'
-Requires-Dist: tree-sitter-typescript>=0.20.0 ; extra == 'all-languages'
-Requires-Dist: psycopg2-binary>=2.9.9 ; extra == 'timescale'
-Requires-Dist: graphiti-core>=0.24.1 ; extra == 'graphiti'
-Requires-Dist: pip-audit>=2.6.0 ; extra == 'security'
-Requires-Dist: cyclonedx-bom>=4.0.0 ; extra == 'security'
-Requires-Dist: prometheus-client>=0.19.0 ; extra == 'observability'
-Requires-Dist: opentelemetry-api>=1.20.0 ; extra == 'observability'
-Requires-Dist: opentelemetry-sdk>=1.20.0 ; extra == 'observability'
-Requires-Dist: opentelemetry-exporter-otlp>=1.20.0 ; extra == 'observability'
-Requires-Dist: sentry-sdk[fastapi,celery,sqlalchemy]>=2.0.0 ; extra == 'observability'
+Requires-Dist: lancedb>=0.4.0 ; extra == 'lancedb'
+Requires-Dist: pyarrow>=14.0.0 ; extra == 'lancedb'
 Requires-Dist: questionary>=2.0.0 ; extra == 'ml'
 Requires-Dist: scikit-learn>=1.3.0 ; extra == 'ml'
 Requires-Dist: joblib>=1.3.0 ; extra == 'ml'
 Requires-Dist: torch>=2.5.0,<2.9.0 ; extra == 'ml'
 Requires-Dist: torch-geometric>=2.6.0 ; extra == 'ml'
 Requires-Dist: gensim>=4.3.0 ; extra == 'ml'
+Requires-Dist: prometheus-client>=0.19.0 ; extra == 'observability'
+Requires-Dist: opentelemetry-api>=1.20.0 ; extra == 'observability'
+Requires-Dist: opentelemetry-sdk>=1.20.0 ; extra == 'observability'
+Requires-Dist: opentelemetry-exporter-otlp>=1.20.0 ; extra == 'observability'
 Requires-Dist: e2b-code-interpreter>=1.0.0 ; extra == 'sandbox'
+Requires-Dist: pip-audit>=2.6.0 ; extra == 'security'
+Requires-Dist: cyclonedx-bom>=4.0.0 ; extra == 'security'
 Requires-Dist: voyageai>=0.3.0 ; extra == 'voyage'
-Requires-Dist: anthropic>=0.40.0 ; extra == 'anthropic'
-Provides-Extra: dev
-Provides-Extra: config
-Provides-Extra: gds
 Provides-Extra: all-languages
-Provides-Extra: timescale
-Provides-Extra: graphiti
-Provides-Extra: security
+Provides-Extra: anthropic
+Provides-Extra: config
+Provides-Extra: dev
+Provides-Extra: lancedb
 Provides-Extra: local-embeddings
-Provides-Extra: observability
 Provides-Extra: ml
+Provides-Extra: observability
 Provides-Extra: sandbox
+Provides-Extra: security
+Provides-Extra: timescale
 Provides-Extra: voyage
-Provides-Extra: anthropic
 License-File: LICENSE
 Summary: Graph-Powered Code Health Platform
-Keywords: code-analysis,knowledge-graph,technical-debt,neo4j,static-analysis
+Keywords: code-analysis,knowledge-graph,technical-debt,falkordb,static-analysis
 Author: Repotoire Team
 License-Expression: MIT
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
-Project-URL: Homepage, https://github.com/yourusername/repotoire
 Project-URL: Documentation, https://repotoire.readthedocs.io
-Project-URL: Repository, https://github.com/yourusername/repotoire
+Project-URL: Homepage, https://github.com/yourusername/repotoire
 Project-URL: Issues, https://github.com/yourusername/repotoire/issues
+Project-URL: Repository, https://github.com/yourusername/repotoire
 
 # Repotoire 🐉
 

{repotoire-0.1.3 → repotoire-0.1.4}/pyproject.toml

@@ -4,20 +4,19 @@ build-backend = "maturin"
 
 [project]
 name = "repotoire"
-version = "0.1.3"
+version = "0.1.4"
 description = "Graph-Powered Code Health Platform"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 license = "MIT"
 authors = [
     {name = "Repotoire Team"}
 ]
-keywords = ["code-analysis", "knowledge-graph", "technical-debt", "neo4j", "static-analysis"]
+keywords = ["code-analysis", "knowledge-graph", "technical-debt", "falkordb", "static-analysis"]
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Intended Audience :: Developers",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
@@ -35,13 +34,12 @@ dependencies = [
     "jinja2>=3.1.0",
     "detect-secrets>=1.4.0",
     "gitpython>=3.1.40",
-    "neo4j-graphrag>=1.10.1",
     "fastapi>=0.121.3",
     "uvicorn>=0.38.0",
     "mcp>=1.22.0",
     "python-dotenv>=1.2.1",
     "clerk-backend-api>=4.2.0",  # v4.2.0+ has api_keys.verify() for API Key auth
-    "httpx>=0.27.0",
+    "httpx[http2]>=0.27.0",
     "pyjwt[crypto]>=2.8.0",  # JWT generation for GitHub App auth
     "cryptography>=41.0.0",  # Token encryption at rest
     "svix>=1.0.0",  # Clerk webhook signature verification
@@ -55,6 +53,7 @@ dependencies = [
     "celery>=5.3.0",  # Distributed task queue for background jobs
     "redis>=5.0.0",  # Redis client for Celery broker
     "structlog>=24.0.0",  # Structured logging for workers
+    "psutil>=5.9.0",  # Memory profiling for worker tasks
     "sentry-sdk[fastapi,celery,sqlalchemy]>=2.0.0",  # Error tracking
     "resend>=0.5.0",  # Email service for notifications
     "aioboto3>=13.0.0",  # Async AWS SES client for non-blocking email sending
@@ -69,6 +68,7 @@ dependencies = [
     "sentence-transformers>=2.2.0",  # Local embedding models + contrastive learning
     "accelerate>=0.26.0",  # Required for PyTorch Trainer
     # Hybrid detector dependencies (core feature)
+    "ruff>=0.1.0",  # Fast linting detector (RuffLintDetector)
     "mypy>=1.7.0",  # Type checking detector
     "pylint>=3.0.0",  # Advanced linting detector
     "bandit>=1.7.0",  # Security vulnerability detector
@@ -87,39 +87,34 @@ dev = [
     "pytest-timeout>=2.2.0",  # Test timeout support
     "hypothesis>=6.100.0",  # Property-based testing for differential tests
     "factory-boy>=3.3.0",  # Test data factories for SQLAlchemy models
-    "httpx>=0.27.0",  # Async HTTP client for API tests
+    "aiosqlite>=0.20.0",  # Async SQLite for unit tests
+    # Note: httpx, mypy, redis already in core dependencies
     "black>=23.0.0",
     "ruff>=0.1.0",
-    "mypy>=1.7.0",
     "pyyaml>=6.0",  # For YAML config support in tests
     "tomli>=2.0.0",  # For TOML support on Python <3.11
     "tenacity>=8.2.0",  # Retry logic for flaky tests (REPO-366)
-    "redis>=5.0.0",  # Redis client for FalkorDB readiness checks
 ]
 
 config = [
     "pyyaml>=6.0",  # YAML config file support (.reporc)
-    "tomli>=2.0.0; python_version < '3.11'",  # TOML support for older Python
+    # tomllib is builtin in Python 3.11+
 ]
 
-gds = [
-    "graphdatascience>=1.9.0",  # Neo4j Graph Data Science
-]
 
 all-languages = [
     "tree-sitter>=0.20.0",
     "tree-sitter-python>=0.20.0",
     "tree-sitter-javascript>=0.20.0",
     "tree-sitter-typescript>=0.20.0",
+    "tree-sitter-java>=0.23.0",
+    "tree-sitter-go>=0.23.0",
 ]
 
 timescale = [
-    "psycopg2-binary>=2.9.9",  # PostgreSQL adapter for TimescaleDB metrics storage
+    # Note: psycopg2-binary already in core dependencies
 ]
 
-graphiti = [
-    "graphiti-core>=0.24.1",  # Temporal knowledge graph for git history tracking
-]
 
 security = [
     "pip-audit>=2.6.0",  # Dependency vulnerability scanning (fallback)
@@ -135,7 +130,7 @@ observability = [
     "opentelemetry-api>=1.20.0",  # OpenTelemetry tracing API
     "opentelemetry-sdk>=1.20.0",  # OpenTelemetry SDK
     "opentelemetry-exporter-otlp>=1.20.0",  # OTLP exporter for distributed tracing
-    "sentry-sdk[fastapi,celery,sqlalchemy]>=2.0.0",  # Error tracking and performance monitoring (REPO-271)
+    # Note: sentry-sdk already in core dependencies
 ]
 
 ml = [
@@ -153,6 +148,11 @@ sandbox = [
     "e2b-code-interpreter>=1.0.0",  # E2B cloud sandbox for secure code execution
 ]
 
+lancedb = [
+    "lancedb>=0.4.0",  # Disk-backed vector DB (zero-copy via Apache Arrow)
+    "pyarrow>=14.0.0",  # Arrow for efficient data transfer
+]
+
 voyage = [
     "voyageai>=0.3.0",  # Voyage AI embeddings (code-optimized, Anthropic-recommended)
 ]
@@ -188,7 +188,7 @@ features = ["pyo3/extension-module"]
 
 [tool.black]
 line-length = 100
-target-version = ['py310', 'py311', 'py312']
+target-version = ['py311', 'py312', 'py313']
 
 [tool.ruff]
 line-length = 100
@@ -196,7 +196,7 @@ select = ["E", "F", "I", "N", "W"]
 ignore = ["E501"]  # Line too long (handled by black)
 
 [tool.mypy]
-python_version = "3.10"
+python_version = "3.11"
 warn_return_any = true
 warn_unused_configs = true
 disallow_untyped_defs = true
@@ -214,15 +214,24 @@ markers = [
     "e2b: Tests requiring E2B sandbox (requires E2B_API_KEY)",
     "slow: Slow tests (>30 seconds)",
     "benchmark: Performance benchmark tests",
-    "neo4j: Tests requiring Neo4j connection",
     "falkordb: Tests requiring FalkorDB connection",
     "anyio: Async tests using anyio",
 ]
+# Async test mode - auto-detects and handles async fixtures/tests
+asyncio_mode = "auto"
 # Filter warnings
 filterwarnings = [
     "ignore::DeprecationWarning",
     "ignore::PendingDeprecationWarning",
 ]
+# Exclude sample repos from test collection (they have their own pyproject.toml)
+norecursedirs = [
+    "tests/fixtures/sample_repos",
+    ".git",
+    ".venv",
+    "node_modules",
+    "__pycache__",
+]
 
 [dependency-groups]
 dev = [
@@ -234,7 +243,7 @@ dev = [
 
 # Bump My Version configuration for semantic versioning
 [tool.bumpversion]
-current_version = "0.1.2"
+current_version = "0.1.4"
 commit = true
 commit_args = "--no-verify"
 tag = true

{repotoire-0.1.3 → repotoire-0.1.4}/repotoire/__init__.py

@@ -5,10 +5,10 @@ Analyzes codebases using knowledge graphs to detect code smells,
 architectural issues, and technical debt.
 """
 
-__version__ = "0.1.2"
+__version__ = "0.1.4"
 
 from repotoire.pipeline import IngestionPipeline
-from repotoire.graph import Neo4jClient
+from repotoire.graph import FalkorDBClient
 from repotoire.detectors import AnalysisEngine
 from repotoire.models import CodebaseHealth, Finding
 

{repotoire-0.1.3 → repotoire-0.1.4}/repotoire/ai/__init__.py

@@ -6,6 +6,11 @@ from repotoire.ai.embeddings import (
     EmbeddingConfig,
     EmbeddingBackend,
     create_embedder,
+    # Int8 quantization for memory-efficient storage
+    quantize_embedding,
+    dequantize_embedding,
+    quantize_embeddings_batch,
+    compute_cosine_similarity_quantized,
 )
 from repotoire.ai.retrieval import (
     GraphRAGRetriever,
@@ -43,6 +48,13 @@ from repotoire.ai.contextual import (
     ContextGenerationResult,
     create_context_generator,
 )
+from repotoire.ai.compression import (
+    EmbeddingCompressor,
+    TenantCompressor,
+    create_compressor,
+    estimate_memory_savings,
+    DEFAULT_TARGET_DIMS,
+)
 
 __all__ = [
     # NLP
@@ -52,6 +64,11 @@ __all__ = [
     "EmbeddingConfig",
     "EmbeddingBackend",
     "create_embedder",
+    # Int8 quantization (4x memory reduction)
+    "quantize_embedding",
+    "dequantize_embedding",
+    "quantize_embeddings_batch",
+    "compute_cosine_similarity_quantized",
     # Retrieval
     "GraphRAGRetriever",
     "RetrievalResult",
@@ -83,4 +100,10 @@ __all__ = [
     "CostLimitExceeded",
     "ContextGenerationResult",
     "create_context_generator",
+    # Compression (memory optimization)
+    "EmbeddingCompressor",
+    "TenantCompressor",
+    "create_compressor",
+    "estimate_memory_savings",
+    "DEFAULT_TARGET_DIMS",
 ]