Files
nextcloud-mcp-server/pyproject.toml
T
Chris Coutinho b8010270c1 fix: Add async/await, PDF metadata, and type safety fixes
This commit addresses multiple issues with async operations, PDF metadata
extraction, and type safety in document processing and search.

## Async/Await Fixes
- processor.py:259 - Added await for chunker.chunk_text(content)
- processor.py:270 - Added await for bm25_service.encode_batch(chunk_texts)
- tests/unit/test_document_chunker.py - Converted all 12 test methods to async

## PDF Metadata Enhancement
- pymupdf.py:143 - Added file_size metadata extraction
- pymupdf.py:145-206 - Refactored to extract text page-by-page
  - Manually loop through pages instead of using page_chunks=True
  - Generate page_boundaries metadata for precise page tracking
  - Works around pymupdf.layout.activate() breaking page_chunks=True
- processor.py:32-66 - Added assign_page_numbers() helper function
  - Assigns page numbers to chunks based on overlap with page boundaries
  - Handles chunks spanning multiple pages
- processor.py:298-300 - Call assign_page_numbers() for PDF files

## Type Safety Fixes
- bm25_hybrid.py:184 - Removed int() conversion of doc_id
- semantic.py:131 - Removed int() conversion of doc_id
- viz_routes.py:275 - Removed int() conversion of doc_id
- Added comments documenting that doc_id can be int (notes) or str (file paths)

## Testing
- All 18 tests passing (12 unit + 6 integration)
- No type errors in modified files
- Container logs show successful processing
- Vector viz searches working correctly

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-20 02:37:07 +01:00

135 lines
4.5 KiB
TOML

[project]
name = "nextcloud-mcp-server"
version = "0.44.0"
description = "Model Context Protocol (MCP) server for Nextcloud integration - enables AI assistants to interact with Nextcloud data"
authors = [
{name = "Chris Coutinho", email = "chris@coutinho.io"}
]
readme = "README.md"
license = {text = "AGPL-3.0-only"}
requires-python = ">=3.11"
keywords = ["nextcloud", "mcp", "model-context-protocol", "llm", "ai", "claude", "webdav", "caldav", "carddav"]
dependencies = [
"mcp[cli] (>=1.21,<1.22)",
"httpx (>=0.28.1,<0.29.0)",
"pillow (>=10.3.0,<12.0.0)", # Compatible with fastembed
"icalendar (>=6.0.0,<7.0.0)",
"pythonvcard4>=0.2.0",
"pydantic>=2.11.4",
"click>=8.1.8",
"caldav",
"pyjwt[crypto]>=2.8.0",
"aiosqlite>=0.20.0", # Async SQLite for refresh token storage
"authlib>=1.6.5",
"qdrant-client>=1.7.0",
"fastembed>=0.7.3", # BM25 sparse vector embeddings for hybrid search
"anthropic>=0.42.0", # For RAG evaluation with Anthropic LLMs
"boto3>=1.35.0", # For Amazon Bedrock provider (optional)
# Observability dependencies
"prometheus-client>=0.21.0", # Prometheus metrics
"opentelemetry-api>=1.28.2", # OpenTelemetry API
"opentelemetry-sdk>=1.28.2", # OpenTelemetry SDK
"opentelemetry-instrumentation-asgi>=0.49b2", # Auto-instrument ASGI/Starlette
"opentelemetry-instrumentation-httpx>=0.49b2", # Auto-instrument httpx client
"opentelemetry-instrumentation-logging>=0.49b2", # Logging integration
"opentelemetry-exporter-otlp-proto-grpc>=1.28.2", # OTLP gRPC exporter
"python-json-logger>=3.2.0", # Structured JSON logging
"jinja2>=3.1.6",
"langchain-text-splitters>=1.0.0",
"pymupdf>=1.26.6",
"pymupdf4llm>=0.2.2",
"pymupdf-layout>=1.26.6",
]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"License :: OSI Approved :: GNU Affero General Public License v3",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Communications",
"Topic :: Internet :: WWW/HTTP",
]
[project.urls]
Homepage = "https://github.com/cbcoutinho/nextcloud-mcp-server"
Documentation = "https://github.com/cbcoutinho/nextcloud-mcp-server#readme"
Repository = "https://github.com/cbcoutinho/nextcloud-mcp-server"
"Bug Tracker" = "https://github.com/cbcoutinho/nextcloud-mcp-server/issues"
Changelog = "https://github.com/cbcoutinho/nextcloud-mcp-server/blob/master/CHANGELOG.md"
[tool.pytest.ini_options]
anyio_mode = "auto"
addopts = "-p no:asyncio -x" # Disable pytest-asyncio plugin, use only anyio
log_cli = 1
log_cli_level = "ERROR"
log_level = "ERROR"
markers = [
"unit: Fast unit tests with mocked dependencies",
"integration: Integration tests requiring Docker containers",
"oauth: OAuth tests requiring Playwright (slowest)",
"smoke: Critical path smoke tests for quick validation",
"keycloak: OAuth tests that utilize keycloak external identity provider",
]
testpaths = [
"tests",
]
# Timeout settings to prevent tests from hanging indefinitely
timeout = 180 # 3 minutes default timeout per test (includes fixture setup)
timeout_func_only = false # Timeout includes fixture setup/teardown
[tool.commitizen]
name = "cz_conventional_commits"
tag_format = "v$version"
version_scheme = "pep440"
version_provider = "uv"
update_changelog_on_bump = true
major_version_zero = true
version_files = [
"charts/nextcloud-mcp-server/Chart.yaml:appVersion",
"charts/nextcloud-mcp-server/Chart.yaml:version"
]
ignored_tag_formats = [
"nextcloud-mcp-server-*"
]
[tool.ruff.lint]
extend-select = ["I"]
[tool.uv.sources]
caldav = { git = "https://github.com/cbcoutinho/caldav", branch = "feature/httpx" }
[build-system]
requires = ["uv_build>=0.9.4,<0.10.0"]
build-backend = "uv_build"
[tool.uv.build-backend]
module-name = "nextcloud_mcp_server"
module-root = ""
[dependency-groups]
dev = [
"commitizen>=4.8.2",
"datasets>=3.3.0", # For BeIR nfcorpus dataset loading
"ipython>=9.2.0",
"playwright>=1.49.1",
"pytest>=8.3.5",
"pytest-cov>=6.1.1",
"pytest-mock>=3.15.1",
"pytest-playwright-asyncio>=0.7.1",
"pytest-timeout>=2.3.1",
"ruff>=0.11.13",
"reportlab>=4.0.0",
"ty>=0.0.1a25",
]
[project.scripts]
nextcloud-mcp-server = "nextcloud_mcp_server.cli:run"
[[tool.uv.index]]
name = "testpypi"
url = "https://test.pypi.org/simple/"
publish-url = "https://test.pypi.org/legacy/"
explicit = true