Files
skill-seekers-reference/src/skill_seekers/cli/arguments/package.py
yusyus 064405c052 fix: resolve 18 bugs and code quality issues across adaptors, CLI, and chunking pipeline
Bug fixes:
- Fix --var flag silently dropped in create routing (args.workflow_var → args.var)
- Fix double _score_code_quality() call in word scraper
- Add .docx file extension validation in WordToSkillConverter
- Fix weaviate ImportError masked by generic Exception handler
- Fix RAG chunking crash using non-existent converter.output_dir

Chunking pipeline improvements:
- Wire --chunk-overlap-tokens through entire package pipeline
  (package_skill → adaptor.package → format_skill_md → _maybe_chunk_content → RAGChunker)
- Add auto-scaling overlap: max(50, chunk_tokens//10) when chunk size is non-default
- Rename --no-preserve-code to --no-preserve-code-blocks (backward-compat alias kept)
- Replace hardcoded 512/50 chunk defaults with DEFAULT_CHUNK_TOKENS/DEFAULT_CHUNK_OVERLAP_TOKENS
  constants across all 12 concrete adaptors, rag_chunker, base, and package_skill

Code quality:
- Extract shared _generate_openai_embeddings() and _generate_st_embeddings() to SkillAdaptor
  base class, removing ~150 lines of duplication from chroma/weaviate/pinecone
- Add Pinecone adaptor with full upload support (pinecone_adaptor.py)

Tests (14 new):
- chunk_overlap_tokens parameter wiring, auto-scaling overlap, preserve_code_blocks flag
- .docx/.doc/no-extension file validation, --var flag routing E2E
- Embedding method inheritance verification, backward-compatible flag aliases

Docs:
- Update CHANGELOG, CLI_REFERENCE, API_REFERENCE, packaging guide (EN+ZH)
- Update README test count badge (1880+ → 2283+)

All 2283 tests passing, 8 skipped, 0 failures.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 21:57:59 +03:00

153 lines
4.5 KiB
Python

"""Package command argument definitions.
This module defines ALL arguments for the package command in ONE place.
Both package_skill.py (standalone) and parsers/package_parser.py (unified CLI)
import and use these definitions.
"""
import argparse
from typing import Any
from .common import DEFAULT_CHUNK_TOKENS, DEFAULT_CHUNK_OVERLAP_TOKENS
PACKAGE_ARGUMENTS: dict[str, dict[str, Any]] = {
# Positional argument
"skill_directory": {
"flags": ("skill_directory",),
"kwargs": {
"type": str,
"help": "Skill directory path (e.g., output/react/)",
},
},
# Control options
"no_open": {
"flags": ("--no-open",),
"kwargs": {
"action": "store_true",
"help": "Don't open output folder after packaging",
},
},
"skip_quality_check": {
"flags": ("--skip-quality-check",),
"kwargs": {
"action": "store_true",
"help": "Skip quality checks before packaging",
},
},
# Target platform
"target": {
"flags": ("--target",),
"kwargs": {
"type": str,
"choices": [
"claude",
"gemini",
"openai",
"markdown",
"langchain",
"llama-index",
"haystack",
"weaviate",
"chroma",
"faiss",
"qdrant",
"pinecone",
],
"default": "claude",
"help": "Target LLM platform (default: claude)",
"metavar": "PLATFORM",
},
},
"upload": {
"flags": ("--upload",),
"kwargs": {
"action": "store_true",
"help": "Automatically upload after packaging (requires platform API key)",
},
},
# Streaming options
"streaming": {
"flags": ("--streaming",),
"kwargs": {
"action": "store_true",
"help": "Use streaming ingestion for large docs (memory-efficient)",
},
},
"streaming_chunk_chars": {
"flags": ("--streaming-chunk-chars",),
"kwargs": {
"type": int,
"default": 4000,
"help": "Maximum characters per chunk (streaming mode, default: 4000)",
"metavar": "N",
},
},
"streaming_overlap_chars": {
"flags": ("--streaming-overlap-chars",),
"kwargs": {
"type": int,
"default": 200,
"help": "Character overlap between chunks (streaming mode, default: 200)",
"metavar": "N",
},
},
"batch_size": {
"flags": ("--batch-size",),
"kwargs": {
"type": int,
"default": 100,
"help": "Number of chunks per batch (streaming mode, default: 100)",
"metavar": "N",
},
},
# RAG chunking options
"chunk_for_rag": {
"flags": ("--chunk-for-rag",),
"kwargs": {
"action": "store_true",
"help": "Enable intelligent chunking for RAG platforms (auto-enabled for RAG adaptors)",
},
},
"chunk_tokens": {
"flags": ("--chunk-tokens",),
"kwargs": {
"type": int,
"default": DEFAULT_CHUNK_TOKENS,
"help": f"Maximum tokens per chunk (default: {DEFAULT_CHUNK_TOKENS})",
"metavar": "N",
},
},
"chunk_overlap_tokens": {
"flags": ("--chunk-overlap-tokens",),
"kwargs": {
"type": int,
"default": DEFAULT_CHUNK_OVERLAP_TOKENS,
"help": f"Overlap between chunks in tokens (default: {DEFAULT_CHUNK_OVERLAP_TOKENS})",
"metavar": "N",
},
},
"no_preserve_code_blocks": {
"flags": ("--no-preserve-code-blocks",),
"kwargs": {
"action": "store_true",
"help": "Allow code block splitting (default: code blocks preserved)",
},
},
}
def add_package_arguments(parser: argparse.ArgumentParser) -> None:
"""Add all package command arguments to a parser."""
for arg_name, arg_def in PACKAGE_ARGUMENTS.items():
flags = arg_def["flags"]
kwargs = arg_def["kwargs"]
parser.add_argument(*flags, **kwargs)
# Deprecated alias for backward compatibility (removed in v4.0.0)
parser.add_argument(
"--no-preserve-code",
dest="no_preserve_code_blocks",
action="store_true",
help=argparse.SUPPRESS,
)