mirror of
https://github.com/JuliusBrussee/caveman.git
synced 2026-08-11 13:21:09 +02:00
refactor: consolidate caveman-compress into skills/caveman-compress, eliminate compress mirror
- Move caveman-compress/ source (SKILL.md, scripts/, README.md, SECURITY.md) to skills/caveman-compress/. - Delete skills/compress/ — the CI-generated rename mirror that caused dual-source confusion. - Move plugins/caveman/skills/compress/ to plugins/caveman/skills/caveman-compress/. Plugin keeps the consolidated name; CI no longer rewrites the frontmatter. - Replace the two sed-heavy CI sync steps with one verbatim cp -r from source to plugin. - Update verify_repo.py, test_compress_safety.py, test_validate_inline.py, GEMINI.md, AGENTS.md, CONTRIBUTING.md, README.md, and the workflow paths to reference the new location. - Use Path.resolve().parents[N] for the benchmark.py repo-root walk now that the directory depth changed. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Julius Brussee
co-authored by
Claude Opus 4.7
Claude Opus 4.7
parent
4e1fdca273
commit
086c43077d
@@ -8,8 +8,8 @@ on:
|
||||
- skills/cavecrew/SKILL.md
|
||||
- agents/cavecrew-*.md
|
||||
- rules/caveman-activate.md
|
||||
- caveman-compress/SKILL.md
|
||||
- caveman-compress/scripts/**
|
||||
- skills/caveman-compress/SKILL.md
|
||||
- skills/caveman-compress/scripts/**
|
||||
|
||||
concurrency:
|
||||
group: sync-skill
|
||||
@@ -39,28 +39,14 @@ jobs:
|
||||
mkdir -p .windsurf/skills/caveman
|
||||
cp skills/caveman/SKILL.md .windsurf/skills/caveman/SKILL.md
|
||||
|
||||
- name: Sync compress skill
|
||||
- name: Sync caveman-compress skill to plugin
|
||||
run: |
|
||||
# Sync to skills/compress (main location for Gemini CLI)
|
||||
rm -rf skills/compress/scripts
|
||||
cp caveman-compress/SKILL.md skills/compress/SKILL.md
|
||||
sed -i 's/^name: caveman-compress$/name: compress/' skills/compress/SKILL.md
|
||||
sed -i "s|The compression scripts live in \`caveman-compress/scripts/\` (adjacent to this SKILL.md). If the path is not immediately available, search for \`caveman-compress/scripts/__main__.py\`.|This SKILL.md lives alongside \`scripts/\` in the same directory. Find that directory.|" skills/compress/SKILL.md
|
||||
sed -i 's|cd caveman-compress && python3|cd <directory_containing_this_SKILL.md> \&\& python3|' skills/compress/SKILL.md
|
||||
cp -r caveman-compress/scripts skills/compress/scripts
|
||||
rm -rf skills/compress/scripts/__pycache__
|
||||
|
||||
- name: Sync compress skill to plugin
|
||||
run: |
|
||||
# Copy SKILL.md and patch name + process instructions for plugin context
|
||||
cp caveman-compress/SKILL.md plugins/caveman/skills/compress/SKILL.md
|
||||
sed -i 's/^name: caveman-compress$/name: compress/' plugins/caveman/skills/compress/SKILL.md
|
||||
sed -i "s|The compression scripts live in \`caveman-compress/scripts/\` (adjacent to this SKILL.md). If the path is not immediately available, search for \`caveman-compress/scripts/__main__.py\`.|This SKILL.md lives alongside \`scripts/\` in the same directory. Find that directory.|" plugins/caveman/skills/compress/SKILL.md
|
||||
sed -i 's|cd caveman-compress && python3|cd <directory_containing_this_SKILL.md> \&\& python3|' plugins/caveman/skills/compress/SKILL.md
|
||||
# Copy scripts verbatim
|
||||
rm -rf plugins/caveman/skills/compress/scripts
|
||||
cp -r caveman-compress/scripts plugins/caveman/skills/compress/scripts
|
||||
rm -rf plugins/caveman/skills/compress/scripts/__pycache__
|
||||
# Plugin distribution mirrors source verbatim — no rename, no sed.
|
||||
mkdir -p plugins/caveman/skills/caveman-compress
|
||||
cp skills/caveman-compress/SKILL.md plugins/caveman/skills/caveman-compress/SKILL.md
|
||||
rm -rf plugins/caveman/skills/caveman-compress/scripts
|
||||
cp -r skills/caveman-compress/scripts plugins/caveman/skills/caveman-compress/scripts
|
||||
rm -rf plugins/caveman/skills/caveman-compress/scripts/__pycache__
|
||||
|
||||
- name: Sync cavecrew skill + agents to plugin
|
||||
run: |
|
||||
@@ -96,8 +82,8 @@ jobs:
|
||||
run: |
|
||||
git add \
|
||||
caveman/SKILL.md \
|
||||
skills/compress/ \
|
||||
plugins/caveman/skills/compress/ \
|
||||
skills/caveman-compress/ \
|
||||
plugins/caveman/skills/caveman-compress/ \
|
||||
plugins/caveman/skills/caveman/SKILL.md \
|
||||
plugins/caveman/skills/cavecrew/SKILL.md \
|
||||
plugins/caveman/agents/cavecrew-investigator.md \
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
@./skills/caveman/SKILL.md
|
||||
@./skills/caveman-commit/SKILL.md
|
||||
@./skills/caveman-review/SKILL.md
|
||||
@./caveman-compress/SKILL.md
|
||||
@./skills/caveman-compress/SKILL.md
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
@./skills/caveman/SKILL.md
|
||||
@./skills/caveman-commit/SKILL.md
|
||||
@./skills/caveman-review/SKILL.md
|
||||
@./caveman-compress/SKILL.md
|
||||
@./skills/caveman-compress/SKILL.md
|
||||
|
||||
@@ -244,7 +244,7 @@ Level stick until you change it or session end.
|
||||
| `mixed-with-code.md` | 888 | 560 | **36.9%** |
|
||||
| **Average** | **898** | **481** | **46%** |
|
||||
|
||||
Full docs: [caveman-compress README](caveman-compress/README.md). [Snyk false-positive note](./caveman-compress/SECURITY.md).
|
||||
Full docs: [caveman-compress README](skills/caveman-compress/README.md). [Snyk false-positive note](./skills/caveman-compress/SECURITY.md).
|
||||
|
||||
## caveman-shrink (MCP middleware)
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description: >
|
||||
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format
|
||||
to save input tokens. Preserves all technical substance, code, URLs, and structure.
|
||||
Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md.
|
||||
Trigger: /caveman:compress FILEPATH or "compress memory file"
|
||||
Trigger: /caveman-compress FILEPATH or "compress memory file"
|
||||
---
|
||||
|
||||
# Caveman Compress
|
||||
@@ -15,15 +15,15 @@ Compress natural language files (CLAUDE.md, todos, preferences) into caveman-spe
|
||||
|
||||
## Trigger
|
||||
|
||||
`/caveman:compress <filepath>` or when user asks to compress a memory file.
|
||||
`/caveman-compress <filepath>` or when user asks to compress a memory file.
|
||||
|
||||
## Process
|
||||
|
||||
1. The compression scripts live in `caveman-compress/scripts/` (adjacent to this SKILL.md). If the path is not immediately available, search for `caveman-compress/scripts/__main__.py`.
|
||||
1. The compression scripts live in `scripts/` (adjacent to this SKILL.md). If the path is not immediately available, search for `scripts/__main__.py` next to this SKILL.md.
|
||||
|
||||
2. Run:
|
||||
2. From the directory containing this SKILL.md, run:
|
||||
|
||||
cd caveman-compress && python3 -m scripts <absolute_filepath>
|
||||
python3 -m scripts <absolute_filepath>
|
||||
|
||||
3. The CLI will:
|
||||
- detect file type (no tokens)
|
||||
+3
-1
@@ -56,7 +56,9 @@ def main():
|
||||
return
|
||||
|
||||
# Glob mode: repo_root/tests/caveman-compress/
|
||||
tests_dir = Path(__file__).parent.parent.parent / "tests" / "caveman-compress"
|
||||
# __file__ lives at <repo_root>/plugins/caveman/skills/caveman-compress/scripts/benchmark.py
|
||||
# Walk up six dirs: scripts → caveman-compress → skills → caveman → plugins → repo_root.
|
||||
tests_dir = Path(__file__).resolve().parents[5] / "tests" / "caveman-compress"
|
||||
if not tests_dir.exists():
|
||||
print(f"❌ Tests dir not found: {tests_dir}")
|
||||
sys.exit(1)
|
||||
@@ -1,111 +0,0 @@
|
||||
---
|
||||
name: compress
|
||||
description: >
|
||||
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format
|
||||
to save input tokens. Preserves all technical substance, code, URLs, and structure.
|
||||
Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md.
|
||||
Trigger: /caveman:compress FILEPATH or "compress memory file"
|
||||
---
|
||||
|
||||
# Caveman Compress
|
||||
|
||||
## Purpose
|
||||
|
||||
Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `<filename>.original.md`.
|
||||
|
||||
## Trigger
|
||||
|
||||
`/caveman:compress <filepath>` or when user asks to compress a memory file.
|
||||
|
||||
## Process
|
||||
|
||||
1. This SKILL.md lives alongside `scripts/` in the same directory. Find that directory.
|
||||
|
||||
2. Run:
|
||||
|
||||
cd <directory_containing_this_SKILL.md> && python3 -m scripts <absolute_filepath>
|
||||
|
||||
3. The CLI will:
|
||||
- detect file type (no tokens)
|
||||
- call Claude to compress
|
||||
- validate output (no tokens)
|
||||
- if errors: cherry-pick fix with Claude (targeted fixes only, no recompression)
|
||||
- retry up to 2 times
|
||||
- if still failing after 2 retries: report error to user, leave original file untouched
|
||||
|
||||
4. Return result to user
|
||||
|
||||
## Compression Rules
|
||||
|
||||
### Remove
|
||||
- Articles: a, an, the
|
||||
- Filler: just, really, basically, actually, simply, essentially, generally
|
||||
- Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend"
|
||||
- Hedging: "it might be worth", "you could consider", "it would be good to"
|
||||
- Redundant phrasing: "in order to" → "to", "make sure to" → "ensure", "the reason is because" → "because"
|
||||
- Connective fluff: "however", "furthermore", "additionally", "in addition"
|
||||
|
||||
### Preserve EXACTLY (never modify)
|
||||
- Code blocks (fenced ``` and indented)
|
||||
- Inline code (`backtick content`)
|
||||
- URLs and links (full URLs, markdown links)
|
||||
- File paths (`/src/components/...`, `./config.yaml`)
|
||||
- Commands (`npm install`, `git commit`, `docker build`)
|
||||
- Technical terms (library names, API names, protocols, algorithms)
|
||||
- Proper nouns (project names, people, companies)
|
||||
- Dates, version numbers, numeric values
|
||||
- Environment variables (`$HOME`, `NODE_ENV`)
|
||||
|
||||
### Preserve Structure
|
||||
- All markdown headings (keep exact heading text, compress body below)
|
||||
- Bullet point hierarchy (keep nesting level)
|
||||
- Numbered lists (keep numbering)
|
||||
- Tables (compress cell text, keep structure)
|
||||
- Frontmatter/YAML headers in markdown files
|
||||
|
||||
### Compress
|
||||
- Use short synonyms: "big" not "extensive", "fix" not "implement a solution for", "use" not "utilize"
|
||||
- Fragments OK: "Run tests before commit" not "You should always run tests before committing"
|
||||
- Drop "you should", "make sure to", "remember to" — just state the action
|
||||
- Merge redundant bullets that say the same thing differently
|
||||
- Keep one example where multiple examples show the same pattern
|
||||
|
||||
CRITICAL RULE:
|
||||
Anything inside ``` ... ``` must be copied EXACTLY.
|
||||
Do not:
|
||||
- remove comments
|
||||
- remove spacing
|
||||
- reorder lines
|
||||
- shorten commands
|
||||
- simplify anything
|
||||
|
||||
Inline code (`...`) must be preserved EXACTLY.
|
||||
Do not modify anything inside backticks.
|
||||
|
||||
If file contains code blocks:
|
||||
- Treat code blocks as read-only regions
|
||||
- Only compress text outside them
|
||||
- Do not merge sections around code
|
||||
|
||||
## Pattern
|
||||
|
||||
Original:
|
||||
> You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.
|
||||
|
||||
Compressed:
|
||||
> Run tests before push to main. Catch bugs early, prevent broken prod deploys.
|
||||
|
||||
Original:
|
||||
> The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.
|
||||
|
||||
Compressed:
|
||||
> Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.
|
||||
|
||||
## Boundaries
|
||||
|
||||
- ONLY compress natural language files (.md, .txt, .typ, .typst, .tex, extensionless)
|
||||
- NEVER modify: .py, .js, .ts, .json, .yaml, .yml, .toml, .env, .lock, .css, .html, .xml, .sql, .sh
|
||||
- If file has mixed content (prose + code), compress ONLY the prose sections
|
||||
- If unsure whether something is code or prose, leave it unchanged
|
||||
- Original file is backed up as FILE.original.md before overwriting
|
||||
- Never compress FILE.original.md (skip it)
|
||||
@@ -1,78 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
from pathlib import Path
|
||||
import sys
|
||||
|
||||
# Support both direct execution and module import
|
||||
try:
|
||||
from .validate import validate
|
||||
except ImportError:
|
||||
sys.path.insert(0, str(Path(__file__).parent))
|
||||
from validate import validate
|
||||
|
||||
try:
|
||||
import tiktoken
|
||||
_enc = tiktoken.get_encoding("o200k_base")
|
||||
except ImportError:
|
||||
_enc = None
|
||||
|
||||
|
||||
def count_tokens(text):
|
||||
if _enc is None:
|
||||
return len(text.split()) # fallback: word count
|
||||
return len(_enc.encode(text))
|
||||
|
||||
|
||||
def benchmark_pair(orig_path: Path, comp_path: Path):
|
||||
orig_text = orig_path.read_text()
|
||||
comp_text = comp_path.read_text()
|
||||
|
||||
orig_tokens = count_tokens(orig_text)
|
||||
comp_tokens = count_tokens(comp_text)
|
||||
saved = 100 * (orig_tokens - comp_tokens) / orig_tokens if orig_tokens > 0 else 0.0
|
||||
result = validate(orig_path, comp_path)
|
||||
|
||||
return (comp_path.name, orig_tokens, comp_tokens, saved, result.is_valid)
|
||||
|
||||
|
||||
def print_table(rows):
|
||||
print("\n| File | Original | Compressed | Saved % | Valid |")
|
||||
print("|------|----------|------------|---------|-------|")
|
||||
for r in rows:
|
||||
print(f"| {r[0]} | {r[1]} | {r[2]} | {r[3]:.1f}% | {'✅' if r[4] else '❌'} |")
|
||||
|
||||
|
||||
def main():
|
||||
# Direct file pair: python3 benchmark.py original.md compressed.md
|
||||
if len(sys.argv) == 3:
|
||||
orig = Path(sys.argv[1]).resolve()
|
||||
comp = Path(sys.argv[2]).resolve()
|
||||
if not orig.exists():
|
||||
print(f"❌ Not found: {orig}")
|
||||
sys.exit(1)
|
||||
if not comp.exists():
|
||||
print(f"❌ Not found: {comp}")
|
||||
sys.exit(1)
|
||||
print_table([benchmark_pair(orig, comp)])
|
||||
return
|
||||
|
||||
# Glob mode: repo_root/tests/caveman-compress/
|
||||
tests_dir = Path(__file__).parent.parent.parent / "tests" / "caveman-compress"
|
||||
if not tests_dir.exists():
|
||||
print(f"❌ Tests dir not found: {tests_dir}")
|
||||
sys.exit(1)
|
||||
|
||||
rows = []
|
||||
for orig in sorted(tests_dir.glob("*.original.md")):
|
||||
comp = orig.with_name(orig.stem.removesuffix(".original") + ".md")
|
||||
if comp.exists():
|
||||
rows.append(benchmark_pair(orig, comp))
|
||||
|
||||
if not rows:
|
||||
print("No compressed file pairs found.")
|
||||
return
|
||||
|
||||
print_table(rows)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,10 +1,10 @@
|
||||
---
|
||||
name: compress
|
||||
name: caveman-compress
|
||||
description: >
|
||||
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format
|
||||
to save input tokens. Preserves all technical substance, code, URLs, and structure.
|
||||
Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md.
|
||||
Trigger: /caveman:compress FILEPATH or "compress memory file"
|
||||
Trigger: /caveman-compress FILEPATH or "compress memory file"
|
||||
---
|
||||
|
||||
# Caveman Compress
|
||||
@@ -15,15 +15,15 @@ Compress natural language files (CLAUDE.md, todos, preferences) into caveman-spe
|
||||
|
||||
## Trigger
|
||||
|
||||
`/caveman:compress <filepath>` or when user asks to compress a memory file.
|
||||
`/caveman-compress <filepath>` or when user asks to compress a memory file.
|
||||
|
||||
## Process
|
||||
|
||||
1. This SKILL.md lives alongside `scripts/` in the same directory. Find that directory.
|
||||
1. The compression scripts live in `scripts/` (adjacent to this SKILL.md). If the path is not immediately available, search for `scripts/__main__.py` next to this SKILL.md.
|
||||
|
||||
2. Run:
|
||||
2. From the directory containing this SKILL.md, run:
|
||||
|
||||
cd <directory_containing_this_SKILL.md> && python3 -m scripts <absolute_filepath>
|
||||
python3 -m scripts <absolute_filepath>
|
||||
|
||||
3. The CLI will:
|
||||
- detect file type (no tokens)
|
||||
+3
-1
@@ -56,7 +56,9 @@ def main():
|
||||
return
|
||||
|
||||
# Glob mode: repo_root/tests/caveman-compress/
|
||||
tests_dir = Path(__file__).parent.parent.parent / "tests" / "caveman-compress"
|
||||
# __file__ lives at <repo_root>/skills/caveman-compress/scripts/benchmark.py
|
||||
# Walk up four dirs: scripts → caveman-compress → skills → repo_root.
|
||||
tests_dir = Path(__file__).resolve().parents[3] / "tests" / "caveman-compress"
|
||||
if not tests_dir.exists():
|
||||
print(f"❌ Tests dir not found: {tests_dir}")
|
||||
sys.exit(1)
|
||||
@@ -1,42 +0,0 @@
|
||||
# compress
|
||||
|
||||
Squeeze prose files into caveman speak. Save input tokens forever.
|
||||
|
||||
## What it does
|
||||
|
||||
Compresses natural language memory files (CLAUDE.md, todos, preferences) into caveman-style prose to cut input tokens on every future session. The compressed version overwrites the original; a human-readable backup is saved as `<filename>.original.md`.
|
||||
|
||||
Preserves exactly: code blocks, inline backticks, URLs, file paths, commands, technical terms, proper nouns, version numbers, environment variables, and all markdown structure (headings, bullets, tables, frontmatter). Compresses only the prose around them.
|
||||
|
||||
The skill shells out to a Python CLI (`python3 -m scripts <filepath>`) that calls Claude to compress, validates the output, and cherry-picks targeted fixes if validation fails. Retries up to 2 times. If still failing, the original file is left untouched.
|
||||
|
||||
Requires Python 3.10+.
|
||||
|
||||
## How to invoke
|
||||
|
||||
```
|
||||
/caveman:compress /absolute/path/to/CLAUDE.md
|
||||
```
|
||||
|
||||
Also triggers on "compress memory file" or similar.
|
||||
|
||||
## Example output
|
||||
|
||||
Original:
|
||||
> You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.
|
||||
|
||||
Compressed:
|
||||
> Run tests before push to main. Catch bugs early, prevent broken prod deploys.
|
||||
|
||||
Typical input-token savings: ~46% on long memory files.
|
||||
|
||||
## Boundaries
|
||||
|
||||
- Only compresses prose files: `.md`, `.txt`, `.typ`, `.typst`, `.tex`, extensionless
|
||||
- Never modifies code files: `.py`, `.js`, `.ts`, `.json`, `.yaml`, `.toml`, `.sh`, etc.
|
||||
- Skips `*.original.md` files (its own backups)
|
||||
|
||||
## See also
|
||||
|
||||
- [`SKILL.md`](./SKILL.md) — full compression rules and validation logic
|
||||
- [Caveman README](../../README.md) — repo overview
|
||||
@@ -1,9 +0,0 @@
|
||||
"""Caveman compress scripts.
|
||||
|
||||
This package provides tools to compress natural language markdown files
|
||||
into caveman format to save input tokens.
|
||||
"""
|
||||
|
||||
__all__ = ["cli", "compress", "detect", "validate"]
|
||||
|
||||
__version__ = "1.0.0"
|
||||
@@ -1,3 +0,0 @@
|
||||
from .cli import main
|
||||
|
||||
main()
|
||||
@@ -1,85 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Caveman Compress CLI
|
||||
|
||||
Usage:
|
||||
caveman <filepath>
|
||||
"""
|
||||
|
||||
import sys
|
||||
|
||||
# Force UTF-8 on stdout/stderr before any code can print. Windows consoles
|
||||
# default to cp1252 and crash on the ❌ glyphs in error/validation branches,
|
||||
# masking the real error and leaving the user with a half-compressed file.
|
||||
for _stream in (sys.stdout, sys.stderr):
|
||||
reconfigure = getattr(_stream, "reconfigure", None)
|
||||
if callable(reconfigure):
|
||||
try:
|
||||
reconfigure(encoding="utf-8", errors="replace")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from .compress import compress_file
|
||||
from .detect import detect_file_type, should_compress
|
||||
|
||||
|
||||
def print_usage():
|
||||
print("Usage: caveman <filepath>")
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 2:
|
||||
print_usage()
|
||||
sys.exit(1)
|
||||
|
||||
filepath = Path(sys.argv[1])
|
||||
|
||||
# Check file exists
|
||||
if not filepath.exists():
|
||||
print(f"❌ File not found: {filepath}")
|
||||
sys.exit(1)
|
||||
|
||||
if not filepath.is_file():
|
||||
print(f"❌ Not a file: {filepath}")
|
||||
sys.exit(1)
|
||||
|
||||
filepath = filepath.resolve()
|
||||
|
||||
# Detect file type
|
||||
file_type = detect_file_type(filepath)
|
||||
|
||||
print(f"Detected: {file_type}")
|
||||
|
||||
# Check if compressible
|
||||
if not should_compress(filepath):
|
||||
print("Skipping: file is not natural language (code/config)")
|
||||
sys.exit(0)
|
||||
|
||||
print("Starting caveman compression...\n")
|
||||
|
||||
try:
|
||||
success = compress_file(filepath)
|
||||
|
||||
if success:
|
||||
print("\nCompression completed successfully")
|
||||
backup_path = filepath.with_name(filepath.stem + ".original.md")
|
||||
print(f"Compressed: {filepath}")
|
||||
print(f"Original: {backup_path}")
|
||||
sys.exit(0)
|
||||
else:
|
||||
print("\n❌ Compression failed after retries")
|
||||
sys.exit(2)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("\nInterrupted by user")
|
||||
sys.exit(130)
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n❌ Error: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,254 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Caveman Memory Compression Orchestrator
|
||||
|
||||
Usage:
|
||||
python scripts/compress.py <filepath>
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
OUTER_FENCE_REGEX = re.compile(
|
||||
r"\A\s*(`{3,}|~{3,})[^\n]*\n(.*)\n\1\s*\Z", re.DOTALL
|
||||
)
|
||||
|
||||
# Filenames and paths that almost certainly hold secrets or PII. Compressing
|
||||
# them ships raw bytes to the Anthropic API — a third-party data boundary that
|
||||
# developers on sensitive codebases cannot cross. detect.py already skips .env
|
||||
# by extension, but credentials.md / secrets.txt / ~/.aws/credentials would
|
||||
# slip through the natural-language filter. This is a hard refuse before read.
|
||||
SENSITIVE_BASENAME_REGEX = re.compile(
|
||||
r"(?ix)^("
|
||||
r"\.env(\..+)?"
|
||||
r"|\.netrc"
|
||||
r"|credentials(\..+)?"
|
||||
r"|secrets?(\..+)?"
|
||||
r"|passwords?(\..+)?"
|
||||
r"|id_(rsa|dsa|ecdsa|ed25519)(\.pub)?"
|
||||
r"|authorized_keys"
|
||||
r"|known_hosts"
|
||||
r"|.*\.(pem|key|p12|pfx|crt|cer|jks|keystore|asc|gpg)"
|
||||
r")$"
|
||||
)
|
||||
|
||||
SENSITIVE_PATH_COMPONENTS = frozenset({".ssh", ".aws", ".gnupg", ".kube", ".docker"})
|
||||
|
||||
SENSITIVE_NAME_TOKENS = (
|
||||
"secret", "credential", "password", "passwd",
|
||||
"apikey", "accesskey", "token", "privatekey",
|
||||
)
|
||||
|
||||
|
||||
def is_sensitive_path(filepath: Path) -> bool:
|
||||
"""Heuristic denylist for files that must never be shipped to a third-party API."""
|
||||
name = filepath.name
|
||||
if SENSITIVE_BASENAME_REGEX.match(name):
|
||||
return True
|
||||
lowered_parts = {p.lower() for p in filepath.parts}
|
||||
if lowered_parts & SENSITIVE_PATH_COMPONENTS:
|
||||
return True
|
||||
# Normalize separators so "api-key" and "api_key" both match "apikey".
|
||||
lower = re.sub(r"[_\-\s.]", "", name.lower())
|
||||
return any(tok in lower for tok in SENSITIVE_NAME_TOKENS)
|
||||
|
||||
|
||||
def strip_llm_wrapper(text: str) -> str:
|
||||
"""Strip outer ```markdown ... ``` fence when it wraps the entire output."""
|
||||
m = OUTER_FENCE_REGEX.match(text)
|
||||
if m:
|
||||
return m.group(2)
|
||||
return text
|
||||
|
||||
from .detect import should_compress
|
||||
from .validate import validate
|
||||
|
||||
MAX_RETRIES = 2
|
||||
|
||||
|
||||
# ---------- Claude Calls ----------
|
||||
|
||||
|
||||
def call_claude(prompt: str) -> str:
|
||||
api_key = os.environ.get("ANTHROPIC_API_KEY")
|
||||
if api_key:
|
||||
try:
|
||||
import anthropic
|
||||
|
||||
client = anthropic.Anthropic(api_key=api_key)
|
||||
msg = client.messages.create(
|
||||
model=os.environ.get("CAVEMAN_MODEL", "claude-sonnet-4-5"),
|
||||
max_tokens=8192,
|
||||
messages=[{"role": "user", "content": prompt}],
|
||||
)
|
||||
return strip_llm_wrapper(msg.content[0].text.strip())
|
||||
except ImportError:
|
||||
pass # anthropic not installed, fall back to CLI
|
||||
# Fallback: use claude CLI (handles desktop auth)
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["claude", "--print"],
|
||||
input=prompt,
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=True,
|
||||
)
|
||||
return strip_llm_wrapper(result.stdout.strip())
|
||||
except subprocess.CalledProcessError as e:
|
||||
raise RuntimeError(f"Claude call failed:\n{e.stderr}")
|
||||
|
||||
|
||||
def build_compress_prompt(original: str) -> str:
|
||||
return f"""
|
||||
Compress this markdown into caveman format.
|
||||
|
||||
STRICT RULES:
|
||||
- Do NOT modify anything inside ``` code blocks
|
||||
- Do NOT modify anything inside inline backticks
|
||||
- Preserve ALL URLs exactly
|
||||
- Preserve ALL headings exactly
|
||||
- Preserve file paths and commands
|
||||
- Return ONLY the compressed markdown body — do NOT wrap the entire output in a ```markdown fence or any other fence. Inner code blocks from the original stay as-is; do not add a new outer fence around the whole file.
|
||||
|
||||
Only compress natural language.
|
||||
|
||||
TEXT:
|
||||
{original}
|
||||
"""
|
||||
|
||||
|
||||
def build_fix_prompt(original: str, compressed: str, errors: List[str]) -> str:
|
||||
errors_str = "\n".join(f"- {e}" for e in errors)
|
||||
return f"""You are fixing a caveman-compressed markdown file. Specific validation errors were found.
|
||||
|
||||
CRITICAL RULES:
|
||||
- DO NOT recompress or rephrase the file
|
||||
- ONLY fix the listed errors — leave everything else exactly as-is
|
||||
- The ORIGINAL is provided as reference only (to restore missing content)
|
||||
- Preserve caveman style in all untouched sections
|
||||
|
||||
ERRORS TO FIX:
|
||||
{errors_str}
|
||||
|
||||
HOW TO FIX:
|
||||
- Missing URL: find it in ORIGINAL, restore it exactly where it belongs in COMPRESSED
|
||||
- Code block mismatch: find the exact code block in ORIGINAL, restore it in COMPRESSED
|
||||
- Heading mismatch: restore the exact heading text from ORIGINAL into COMPRESSED
|
||||
- Do not touch any section not mentioned in the errors
|
||||
|
||||
ORIGINAL (reference only):
|
||||
{original}
|
||||
|
||||
COMPRESSED (fix this):
|
||||
{compressed}
|
||||
|
||||
Return ONLY the fixed compressed file. No explanation.
|
||||
"""
|
||||
|
||||
|
||||
# ---------- Core Logic ----------
|
||||
|
||||
|
||||
def compress_file(filepath: Path) -> bool:
|
||||
# Resolve and validate path
|
||||
filepath = filepath.resolve()
|
||||
MAX_FILE_SIZE = 500_000 # 500KB
|
||||
if not filepath.exists():
|
||||
raise FileNotFoundError(f"File not found: {filepath}")
|
||||
if filepath.stat().st_size > MAX_FILE_SIZE:
|
||||
raise ValueError(f"File too large to compress safely (max 500KB): {filepath}")
|
||||
|
||||
# Refuse files that look like they contain secrets or PII. Compressing ships
|
||||
# the raw bytes to the Anthropic API — a third-party boundary — so we fail
|
||||
# loudly rather than silently exfiltrate credentials or keys. Override is
|
||||
# intentional: the user must rename the file if the heuristic is wrong.
|
||||
if is_sensitive_path(filepath):
|
||||
raise ValueError(
|
||||
f"Refusing to compress {filepath}: filename looks sensitive "
|
||||
"(credentials, keys, secrets, or known private paths). "
|
||||
"Compression sends file contents to the Anthropic API. "
|
||||
"Rename the file if this is a false positive."
|
||||
)
|
||||
|
||||
print(f"Processing: {filepath}")
|
||||
|
||||
if not should_compress(filepath):
|
||||
print("Skipping (not natural language)")
|
||||
return False
|
||||
|
||||
original_text = filepath.read_text(errors="ignore")
|
||||
backup_path = filepath.with_name(filepath.stem + ".original.md")
|
||||
|
||||
if not original_text.strip():
|
||||
print("❌ Refusing to compress: file is empty or whitespace-only.")
|
||||
return False
|
||||
|
||||
# Check if backup already exists to prevent accidental overwriting
|
||||
if backup_path.exists():
|
||||
print(f"⚠️ Backup file already exists: {backup_path}")
|
||||
print("The original backup may contain important content.")
|
||||
print("Aborting to prevent data loss. Please remove or rename the backup file if you want to proceed.")
|
||||
return False
|
||||
|
||||
# Step 1: Compress
|
||||
print("Compressing with Claude...")
|
||||
compressed = call_claude(build_compress_prompt(original_text))
|
||||
|
||||
if compressed is None or not compressed.strip():
|
||||
print("❌ Compression aborted: Claude returned an empty response.")
|
||||
print(" Original file is untouched (no backup created).")
|
||||
return False
|
||||
|
||||
if compressed.strip() == original_text.strip():
|
||||
print("❌ Compression aborted: output is identical to input.")
|
||||
print(" Likely causes: Claude refused, returned the prompt verbatim, or the file is")
|
||||
print(" already in caveman form. Original file is untouched (no backup created).")
|
||||
return False
|
||||
|
||||
# Save original as backup, then verify the backup readback before
|
||||
# touching the input file. If the filesystem dropped bytes (encoding,
|
||||
# antivirus, disk full), unlink the bad backup and abort instead of
|
||||
# leaving the user with a corrupt backup + compressed primary.
|
||||
backup_path.write_text(original_text)
|
||||
backup_readback = backup_path.read_text(errors="ignore")
|
||||
if backup_readback != original_text:
|
||||
print(f"❌ Backup write verification failed: {backup_path}")
|
||||
print(" In-memory original differs from on-disk backup. Aborting before touching the input file.")
|
||||
try:
|
||||
backup_path.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
return False
|
||||
filepath.write_text(compressed)
|
||||
|
||||
# Step 2: Validate + Retry
|
||||
for attempt in range(MAX_RETRIES):
|
||||
print(f"\nValidation attempt {attempt + 1}")
|
||||
|
||||
result = validate(backup_path, filepath)
|
||||
|
||||
if result.is_valid:
|
||||
print("Validation passed")
|
||||
break
|
||||
|
||||
print("❌ Validation failed:")
|
||||
for err in result.errors:
|
||||
print(f" - {err}")
|
||||
|
||||
if attempt == MAX_RETRIES - 1:
|
||||
# Restore original on failure
|
||||
filepath.write_text(original_text)
|
||||
backup_path.unlink(missing_ok=True)
|
||||
print("❌ Failed after retries — original restored")
|
||||
return False
|
||||
|
||||
print("Fixing with Claude...")
|
||||
compressed = call_claude(
|
||||
build_fix_prompt(original_text, compressed, result.errors)
|
||||
)
|
||||
filepath.write_text(compressed)
|
||||
|
||||
return True
|
||||
@@ -1,121 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Detect whether a file is natural language (compressible) or code/config (skip)."""
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
# Extensions that are natural language and compressible
|
||||
COMPRESSIBLE_EXTENSIONS = {".md", ".txt", ".markdown", ".rst", ".typ", ".typst", ".tex"}
|
||||
|
||||
# Extensions that are code/config and should be skipped
|
||||
SKIP_EXTENSIONS = {
|
||||
".py", ".js", ".ts", ".tsx", ".jsx", ".json", ".yaml", ".yml",
|
||||
".toml", ".env", ".lock", ".css", ".scss", ".html", ".xml",
|
||||
".sql", ".sh", ".bash", ".zsh", ".go", ".rs", ".java", ".c",
|
||||
".cpp", ".h", ".hpp", ".rb", ".php", ".swift", ".kt", ".lua",
|
||||
".dockerfile", ".makefile", ".csv", ".ini", ".cfg",
|
||||
}
|
||||
|
||||
# Patterns that indicate a line is code
|
||||
CODE_PATTERNS = [
|
||||
re.compile(r"^\s*(import |from .+ import |require\(|const |let |var )"),
|
||||
re.compile(r"^\s*(def |class |function |async function |export )"),
|
||||
re.compile(r"^\s*(if\s*\(|for\s*\(|while\s*\(|switch\s*\(|try\s*\{)"),
|
||||
re.compile(r"^\s*[\}\]\);]+\s*$"), # closing braces/brackets
|
||||
re.compile(r"^\s*@\w+"), # decorators/annotations
|
||||
re.compile(r'^\s*"[^"]+"\s*:\s*'), # JSON-like key-value
|
||||
re.compile(r"^\s*\w+\s*=\s*[{\[\(\"']"), # assignment with literal
|
||||
]
|
||||
|
||||
|
||||
def _is_code_line(line: str) -> bool:
|
||||
"""Check if a line looks like code."""
|
||||
return any(p.match(line) for p in CODE_PATTERNS)
|
||||
|
||||
|
||||
def _is_json_content(text: str) -> bool:
|
||||
"""Check if content is valid JSON."""
|
||||
try:
|
||||
json.loads(text)
|
||||
return True
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
return False
|
||||
|
||||
|
||||
def _is_yaml_content(lines: list[str]) -> bool:
|
||||
"""Heuristic: check if content looks like YAML."""
|
||||
yaml_indicators = 0
|
||||
for line in lines[:30]:
|
||||
stripped = line.strip()
|
||||
if stripped.startswith("---"):
|
||||
yaml_indicators += 1
|
||||
elif re.match(r"^\w[\w\s]*:\s", stripped):
|
||||
yaml_indicators += 1
|
||||
elif stripped.startswith("- ") and ":" in stripped:
|
||||
yaml_indicators += 1
|
||||
# If most non-empty lines look like YAML
|
||||
non_empty = sum(1 for l in lines[:30] if l.strip())
|
||||
return non_empty > 0 and yaml_indicators / non_empty > 0.6
|
||||
|
||||
|
||||
def detect_file_type(filepath: Path) -> str:
|
||||
"""Classify a file as 'natural_language', 'code', 'config', or 'unknown'.
|
||||
|
||||
Returns:
|
||||
One of: 'natural_language', 'code', 'config', 'unknown'
|
||||
"""
|
||||
ext = filepath.suffix.lower()
|
||||
|
||||
# Extension-based classification
|
||||
if ext in COMPRESSIBLE_EXTENSIONS:
|
||||
return "natural_language"
|
||||
if ext in SKIP_EXTENSIONS:
|
||||
return "code" if ext not in {".json", ".yaml", ".yml", ".toml", ".ini", ".cfg", ".env"} else "config"
|
||||
|
||||
# Extensionless files (like CLAUDE.md, TODO) — check content
|
||||
if not ext:
|
||||
try:
|
||||
text = filepath.read_text(errors="ignore")
|
||||
except (OSError, PermissionError):
|
||||
return "unknown"
|
||||
|
||||
lines = text.splitlines()[:50]
|
||||
|
||||
if _is_json_content(text[:10000]):
|
||||
return "config"
|
||||
if _is_yaml_content(lines):
|
||||
return "config"
|
||||
|
||||
code_lines = sum(1 for l in lines if l.strip() and _is_code_line(l))
|
||||
non_empty = sum(1 for l in lines if l.strip())
|
||||
if non_empty > 0 and code_lines / non_empty > 0.4:
|
||||
return "code"
|
||||
|
||||
return "natural_language"
|
||||
|
||||
return "unknown"
|
||||
|
||||
|
||||
def should_compress(filepath: Path) -> bool:
|
||||
"""Return True if the file is natural language and should be compressed."""
|
||||
if not filepath.is_file():
|
||||
return False
|
||||
# Skip backup files
|
||||
if filepath.name.endswith(".original.md"):
|
||||
return False
|
||||
return detect_file_type(filepath) == "natural_language"
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: python detect.py <file1> [file2] ...")
|
||||
sys.exit(1)
|
||||
|
||||
for path_str in sys.argv[1:]:
|
||||
p = Path(path_str).resolve()
|
||||
file_type = detect_file_type(p)
|
||||
compress = should_compress(p)
|
||||
print(f" {p.name:30s} type={file_type:20s} compress={compress}")
|
||||
@@ -1,213 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import re
|
||||
from collections import Counter
|
||||
from pathlib import Path
|
||||
|
||||
URL_REGEX = re.compile(r"https?://[^\s)]+")
|
||||
FENCE_OPEN_REGEX = re.compile(r"^(\s{0,3})(`{3,}|~{3,})(.*)$")
|
||||
HEADING_REGEX = re.compile(r"^(#{1,6})\s+(.*)", re.MULTILINE)
|
||||
BULLET_REGEX = re.compile(r"^\s*[-*+]\s+", re.MULTILINE)
|
||||
|
||||
# crude but effective path detection
|
||||
# Requires either a path prefix (./ ../ / or drive letter) or a slash/backslash within the match
|
||||
PATH_REGEX = re.compile(r"(?:\./|\.\./|/|[A-Za-z]:\\)[\w\-/\\\.]+|[\w\-\.]+[/\\][\w\-/\\\.]+")
|
||||
|
||||
|
||||
class ValidationResult:
|
||||
def __init__(self):
|
||||
self.is_valid = True
|
||||
self.errors = []
|
||||
self.warnings = []
|
||||
|
||||
def add_error(self, msg):
|
||||
self.is_valid = False
|
||||
self.errors.append(msg)
|
||||
|
||||
def add_warning(self, msg):
|
||||
self.warnings.append(msg)
|
||||
|
||||
|
||||
def read_file(path: Path) -> str:
|
||||
return path.read_text(errors="ignore")
|
||||
|
||||
|
||||
# ---------- Extractors ----------
|
||||
|
||||
|
||||
def extract_headings(text):
|
||||
return [(level, title.strip()) for level, title in HEADING_REGEX.findall(text)]
|
||||
|
||||
|
||||
def extract_code_blocks(text):
|
||||
"""Line-based fenced code block extractor.
|
||||
|
||||
Handles ``` and ~~~ fences with variable length (CommonMark: closing
|
||||
fence must use same char and be at least as long as opening). Supports
|
||||
nested fences (e.g. an outer 4-backtick block wrapping inner 3-backtick
|
||||
content).
|
||||
"""
|
||||
blocks = []
|
||||
lines = text.split("\n")
|
||||
i = 0
|
||||
n = len(lines)
|
||||
while i < n:
|
||||
m = FENCE_OPEN_REGEX.match(lines[i])
|
||||
if not m:
|
||||
i += 1
|
||||
continue
|
||||
fence_char = m.group(2)[0]
|
||||
fence_len = len(m.group(2))
|
||||
open_line = lines[i]
|
||||
block_lines = [open_line]
|
||||
i += 1
|
||||
closed = False
|
||||
while i < n:
|
||||
close_m = FENCE_OPEN_REGEX.match(lines[i])
|
||||
if (
|
||||
close_m
|
||||
and close_m.group(2)[0] == fence_char
|
||||
and len(close_m.group(2)) >= fence_len
|
||||
and close_m.group(3).strip() == ""
|
||||
):
|
||||
block_lines.append(lines[i])
|
||||
closed = True
|
||||
i += 1
|
||||
break
|
||||
block_lines.append(lines[i])
|
||||
i += 1
|
||||
if closed:
|
||||
blocks.append("\n".join(block_lines))
|
||||
# Unclosed fences are silently skipped — they indicate malformed markdown
|
||||
# and including them would cause false-positive validation failures.
|
||||
return blocks
|
||||
|
||||
|
||||
def extract_urls(text):
|
||||
return set(URL_REGEX.findall(text))
|
||||
|
||||
|
||||
def extract_paths(text):
|
||||
return set(PATH_REGEX.findall(text))
|
||||
|
||||
|
||||
def count_bullets(text):
|
||||
return len(BULLET_REGEX.findall(text))
|
||||
|
||||
|
||||
def extract_inline_codes(text):
|
||||
text_without_fences = re.sub(r"^```[\s\S]*?^```", "", text, flags=re.MULTILINE)
|
||||
text_without_fences = re.sub(r"^~~~[\s\S]*?^~~~", "", text_without_fences, flags=re.MULTILINE)
|
||||
return re.findall(r"`([^`]+)`", text_without_fences)
|
||||
|
||||
|
||||
# ---------- Validators ----------
|
||||
|
||||
|
||||
def validate_headings(orig, comp, result):
|
||||
h1 = extract_headings(orig)
|
||||
h2 = extract_headings(comp)
|
||||
|
||||
if len(h1) != len(h2):
|
||||
result.add_error(f"Heading count mismatch: {len(h1)} vs {len(h2)}")
|
||||
|
||||
if h1 != h2:
|
||||
result.add_warning("Heading text/order changed")
|
||||
|
||||
|
||||
def validate_code_blocks(orig, comp, result):
|
||||
c1 = extract_code_blocks(orig)
|
||||
c2 = extract_code_blocks(comp)
|
||||
|
||||
if c1 != c2:
|
||||
result.add_error("Code blocks not preserved exactly")
|
||||
|
||||
|
||||
def validate_urls(orig, comp, result):
|
||||
u1 = extract_urls(orig)
|
||||
u2 = extract_urls(comp)
|
||||
|
||||
if u1 != u2:
|
||||
result.add_error(f"URL mismatch: lost={u1 - u2}, added={u2 - u1}")
|
||||
|
||||
|
||||
def validate_paths(orig, comp, result):
|
||||
p1 = extract_paths(orig)
|
||||
p2 = extract_paths(comp)
|
||||
|
||||
if p1 != p2:
|
||||
result.add_warning(f"Path mismatch: lost={p1 - p2}, added={p2 - p1}")
|
||||
|
||||
|
||||
def validate_bullets(orig, comp, result):
|
||||
b1 = count_bullets(orig)
|
||||
b2 = count_bullets(comp)
|
||||
|
||||
if b1 == 0:
|
||||
return
|
||||
|
||||
diff = abs(b1 - b2) / b1
|
||||
|
||||
if diff > 0.15:
|
||||
result.add_warning(f"Bullet count changed too much: {b1} -> {b2}")
|
||||
|
||||
|
||||
def validate_inline_codes(orig, comp, result):
|
||||
c1 = Counter(extract_inline_codes(orig))
|
||||
c2 = Counter(extract_inline_codes(comp))
|
||||
|
||||
if c1 != c2:
|
||||
lost = set(c1.keys()) - set(c2.keys())
|
||||
added = set(c2.keys()) - set(c1.keys())
|
||||
for code, count in c1.items():
|
||||
if code in c2 and c2[code] < count:
|
||||
lost.add(f"{code} (lost {count - c2[code]} of {count} occurrences)")
|
||||
if lost:
|
||||
result.add_error(f"Inline code lost: {lost}")
|
||||
if added:
|
||||
result.add_warning(f"Inline code added: {added}")
|
||||
|
||||
|
||||
# ---------- Main ----------
|
||||
|
||||
|
||||
def validate(original_path: Path, compressed_path: Path) -> ValidationResult:
|
||||
result = ValidationResult()
|
||||
|
||||
orig = read_file(original_path)
|
||||
comp = read_file(compressed_path)
|
||||
|
||||
validate_headings(orig, comp, result)
|
||||
validate_code_blocks(orig, comp, result)
|
||||
validate_urls(orig, comp, result)
|
||||
validate_paths(orig, comp, result)
|
||||
validate_bullets(orig, comp, result)
|
||||
validate_inline_codes(orig, comp, result)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
# ---------- CLI ----------
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
|
||||
if len(sys.argv) != 3:
|
||||
print("Usage: python validate.py <original> <compressed>")
|
||||
sys.exit(1)
|
||||
|
||||
orig = Path(sys.argv[1]).resolve()
|
||||
comp = Path(sys.argv[2]).resolve()
|
||||
|
||||
res = validate(orig, comp)
|
||||
|
||||
print(f"\nValid: {res.is_valid}")
|
||||
|
||||
if res.errors:
|
||||
print("\nErrors:")
|
||||
for e in res.errors:
|
||||
print(f" - {e}")
|
||||
|
||||
if res.warnings:
|
||||
print("\nWarnings:")
|
||||
for w in res.warnings:
|
||||
print(f" - {w}")
|
||||
@@ -15,9 +15,9 @@ from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
sys.path.insert(0, str(REPO_ROOT))
|
||||
sys.path.insert(0, str(REPO_ROOT / "skills" / "caveman-compress"))
|
||||
|
||||
from skills.compress.scripts import compress as compress_mod # noqa: E402
|
||||
from scripts import compress as compress_mod # noqa: E402
|
||||
|
||||
|
||||
class CompressSafetyTests(unittest.TestCase):
|
||||
|
||||
@@ -4,9 +4,9 @@ import unittest
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
sys.path.insert(0, str(REPO_ROOT))
|
||||
sys.path.insert(0, str(REPO_ROOT / "skills" / "caveman-compress"))
|
||||
|
||||
from skills.compress.scripts.validate import ( # noqa: E402
|
||||
from scripts.validate import ( # noqa: E402
|
||||
ValidationResult,
|
||||
extract_inline_codes,
|
||||
validate,
|
||||
|
||||
@@ -109,7 +109,7 @@ def verify_skill_frontmatter_upload_compatibility() -> None:
|
||||
ROOT / "skills/caveman-commit/SKILL.md",
|
||||
ROOT / "skills/caveman-help/SKILL.md",
|
||||
ROOT / "skills/caveman-review/SKILL.md",
|
||||
ROOT / "caveman-compress/SKILL.md",
|
||||
ROOT / "skills/caveman-compress/SKILL.md",
|
||||
]
|
||||
for path in skill_paths:
|
||||
description = _frontmatter_description(path)
|
||||
@@ -210,7 +210,7 @@ def verify_powershell_static() -> None:
|
||||
|
||||
|
||||
def load_compress_modules():
|
||||
sys.path.insert(0, str(ROOT / "caveman-compress"))
|
||||
sys.path.insert(0, str(ROOT / "skills/caveman-compress"))
|
||||
import scripts.benchmark # noqa: F401
|
||||
import scripts.cli as cli
|
||||
import scripts.compress # noqa: F401
|
||||
@@ -241,8 +241,8 @@ def verify_compress_cli() -> None:
|
||||
section("Compress CLI")
|
||||
|
||||
skip_result = run(
|
||||
["python3", "-m", "scripts", "../hooks/install.sh"],
|
||||
cwd=ROOT / "caveman-compress",
|
||||
["python3", "-m", "scripts", "../../hooks/install.sh"],
|
||||
cwd=ROOT / "skills/caveman-compress",
|
||||
check=False,
|
||||
)
|
||||
ensure(skip_result.returncode == 0, "compress CLI skip path should exit 0")
|
||||
@@ -253,8 +253,8 @@ def verify_compress_cli() -> None:
|
||||
)
|
||||
|
||||
missing_result = run(
|
||||
["python3", "-m", "scripts", "../does-not-exist.md"],
|
||||
cwd=ROOT / "caveman-compress",
|
||||
["python3", "-m", "scripts", "../../does-not-exist.md"],
|
||||
cwd=ROOT / "skills/caveman-compress",
|
||||
check=False,
|
||||
)
|
||||
ensure(missing_result.returncode == 1, "compress CLI missing-file path should exit 1")
|
||||
|
||||
Reference in New Issue
Block a user