refactor: rename all chunk flags to include explicit units

Replace ambiguous --chunk-size / --chunk-overlap names that meant different
things in different contexts (tokens vs characters) with fully explicit names:

- --chunk-size (RAG tokens)     → --chunk-tokens
- --chunk-overlap (RAG tokens)  → --chunk-overlap-tokens
- --chunk (enable RAG chunking) → --chunk-for-rag
- --streaming-chunk-size (chars) → --streaming-chunk-chars
- --streaming-overlap (chars)    → --streaming-overlap-chars
- --chunk-size (PDF pages)       → --pdf-pages-per-chunk (poc file)

Also aligns stream_parser.py help with streaming_ingest.py standalone parser.
All 2167 tests pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
yusyus
2026-02-24 22:07:56 +03:00
parent b636a0a292
commit 7a2ffb286c
12 changed files with 40 additions and 40 deletions

View File

@@ -106,8 +106,8 @@ class CreateCommand:
# Check against common defaults
defaults = {
"max_issues": 100,
"chunk_size": 512,
"chunk_overlap": 50,
"chunk_tokens": 512,
"chunk_overlap_tokens": 50,
"output": None,
}
@@ -158,10 +158,10 @@ class CreateCommand:
# RAG arguments (web scraper only)
if getattr(self.args, "chunk_for_rag", False):
argv.append("--chunk-for-rag")
if getattr(self.args, "chunk_size", None) and self.args.chunk_size != 512:
argv.extend(["--chunk-size", str(self.args.chunk_size)])
if getattr(self.args, "chunk_overlap", None) and self.args.chunk_overlap != 50:
argv.extend(["--chunk-overlap", str(self.args.chunk_overlap)])
if getattr(self.args, "chunk_tokens", None) and self.args.chunk_tokens != 512:
argv.extend(["--chunk-tokens", str(self.args.chunk_tokens)])
if getattr(self.args, "chunk_overlap_tokens", None) and self.args.chunk_overlap_tokens != 50:
argv.extend(["--chunk-overlap-tokens", str(self.args.chunk_overlap_tokens)])
# Advanced web-specific arguments
if getattr(self.args, "no_preserve_code_blocks", False):