ghostcode 0.5.0__tar.gz

ghostcode-0.5.0/PKG-INFO

@@ -0,0 +1,92 @@
+Metadata-Version: 2.4
+Name: ghostcode
+Version: 0.5.0
+Summary: Privacy proxy for developers — hide business context before sharing code with AI
+Author: Smit Vaishanav
+License: MIT
+Project-URL: Homepage, https://github.com/smitvaishnav/anti-ai
+Project-URL: Repository, https://github.com/smitvaishnav/anti-ai
+Project-URL: Issues, https://github.com/smitvaishnav/anti-ai/issues
+Keywords: privacy,security,ai,llm,code-anonymization,ghostcode
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Security
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: click>=8.1.0
+Requires-Dist: libclang>=16.0.0
+Requires-Dist: cryptography>=41.0.0
+Requires-Dist: pyyaml>=6.0
+Dynamic: requires-python
+
+# GhostCode — Privacy Proxy for Developers
+
+**Hide your business logic before sharing code with LLMs. Local-first, open-source, zero telemetry.**
+
+GhostCode replaces your private symbols (variable names, functions, strings, comments) with opaque ghost tokens before you share code with AI. The AI sees `gv_001` instead of `customer_revenue`. When you get your answer back, GhostCode restores everything.
+
+## Installation
+
+```bash
+pip install ghostcode
+```
+
+## Quick Start
+
+```bash
+# Hide a file (Level 2: names + comments + literals)
+ghost hide my_code.py --level 2
+
+# Paste the ghost output into ChatGPT/Claude, get a response, save it
+
+# Reveal — restore original names in the AI's response
+ghost reveal ai_response.py --map-file .ghostcode/maps/my_code_*.json
+```
+
+## Privacy Levels
+
+| Level | What it does |
+|-------|-------------|
+| 1 | Rename symbols + strip comments |
+| 2 | + Scrub string/numeric literals |
+| 3 | + Function isolation with stubs |
+| 4 | + Dimension generalization |
+
+## Pre-Send Risk Report
+
+Every `ghost hide` shows a risk assessment:
+- Symbols and literals scrubbed/flagged/kept
+- Structural patterns visible to the AI
+- **Estimated domain exposure: LOW / MEDIUM / HIGH**
+
+## VS Code Extension
+
+Install the [GhostCode VS Code extension](https://marketplace.visualstudio.com/items?itemName=SmitVaishanav.ghostcode) for one-click hide/reveal buttons in the editor toolbar.
+
+## Supported Languages
+
+- Python (.py)
+- C/C++ (.cpp, .cc, .c, .h, .hpp)
+
+## Features
+
+- 🔒 **AST-based symbol renaming** — not regex, real parsing
+- 📊 **Smart literal scrubbing** — keeps `0`, `1`, `pi`; scrubs URLs, API keys, business strings
+- 🗺️ **Ghost Map** — bidirectional mapping stored as JSON
+- 🔐 **Encrypted maps** — optional AES encryption for map files
+- 📋 **Audit logging** — immutable JSON logs for compliance
+- 🔄 **Round-trip reveal** — restores names in both code and AI explanations
+- ⚡ **Zero cloud, zero telemetry** — everything runs locally
+
+## License
+
+MIT

ghostcode-0.5.0/README_PYPI.md

@@ -0,0 +1,62 @@
+# GhostCode — Privacy Proxy for Developers
+
+**Hide your business logic before sharing code with LLMs. Local-first, open-source, zero telemetry.**
+
+GhostCode replaces your private symbols (variable names, functions, strings, comments) with opaque ghost tokens before you share code with AI. The AI sees `gv_001` instead of `customer_revenue`. When you get your answer back, GhostCode restores everything.
+
+## Installation
+
+```bash
+pip install ghostcode
+```
+
+## Quick Start
+
+```bash
+# Hide a file (Level 2: names + comments + literals)
+ghost hide my_code.py --level 2
+
+# Paste the ghost output into ChatGPT/Claude, get a response, save it
+
+# Reveal — restore original names in the AI's response
+ghost reveal ai_response.py --map-file .ghostcode/maps/my_code_*.json
+```
+
+## Privacy Levels
+
+| Level | What it does |
+|-------|-------------|
+| 1 | Rename symbols + strip comments |
+| 2 | + Scrub string/numeric literals |
+| 3 | + Function isolation with stubs |
+| 4 | + Dimension generalization |
+
+## Pre-Send Risk Report
+
+Every `ghost hide` shows a risk assessment:
+- Symbols and literals scrubbed/flagged/kept
+- Structural patterns visible to the AI
+- **Estimated domain exposure: LOW / MEDIUM / HIGH**
+
+## VS Code Extension
+
+Install the [GhostCode VS Code extension](https://marketplace.visualstudio.com/items?itemName=SmitVaishanav.ghostcode) for one-click hide/reveal buttons in the editor toolbar.
+
+## Supported Languages
+
+- Python (.py)
+- C/C++ (.cpp, .cc, .c, .h, .hpp)
+
+## Features
+
+- 🔒 **AST-based symbol renaming** — not regex, real parsing
+- 📊 **Smart literal scrubbing** — keeps `0`, `1`, `pi`; scrubs URLs, API keys, business strings
+- 🗺️ **Ghost Map** — bidirectional mapping stored as JSON
+- 🔐 **Encrypted maps** — optional AES encryption for map files
+- 📋 **Audit logging** — immutable JSON logs for compliance
+- 🔄 **Round-trip reveal** — restores names in both code and AI explanations
+- ⚡ **Zero cloud, zero telemetry** — everything runs locally
+
+## License
+
+MIT

ghostcode-0.5.0/ghostcode/__init__.py

@@ -0,0 +1,3 @@
+"""GhostCode — Privacy Proxy for Developers."""
+
+__version__ = "0.5.0"

ghostcode-0.5.0/ghostcode/audit/logger.py

@@ -0,0 +1,149 @@
+"""Audit logger.
+
+Every ghost hide/reveal invocation produces an immutable JSON log entry.
+The security team can review exactly what was scrubbed, what was kept,
+and what warnings were raised.
+
+Log location: ~/.ghostcode/audit/YYYY-MM-DD.jsonl
+Format: JSON Lines (one JSON object per line, append-only)
+
+Each entry contains:
+    - Timestamp and user info
+    - Action (hide/reveal)
+    - File details and scrub level
+    - Symbol/literal/comment counts
+    - SHA-256 hashes of input and output
+    - Any warnings raised
+"""
+
+import getpass
+import hashlib
+import json
+import os
+import platform
+from datetime import datetime, timezone
+
+
+def _get_audit_dir() -> str:
+    """Get the audit log directory."""
+    return os.path.join(os.path.expanduser("~"), ".ghostcode", "audit")
+
+
+def _hash_content(content: str) -> str:
+    """SHA-256 hash of content."""
+    return hashlib.sha256(content.encode()).hexdigest()
+
+
+def _hash_file(filepath: str) -> str:
+    """SHA-256 hash of a file's contents."""
+    try:
+        with open(filepath, "rb") as f:
+            return hashlib.sha256(f.read()).hexdigest()
+    except (FileNotFoundError, PermissionError):
+        return "unavailable"
+
+
+class AuditLogger:
+    """Append-only audit logger for GhostCode operations."""
+
+    def __init__(self, enabled: bool = True):
+        self._enabled = enabled
+        self._audit_dir = _get_audit_dir()
+
+    def log_hide(self, source_files: list[str], scrub_level: int,
+                 function_isolated: str | None,
+                 symbols_scrubbed: int, literals_scrubbed: int,
+                 literals_flagged: int, literals_kept: int,
+                 comments_stripped: int, warnings: list[dict],
+                 ghost_output_path: str, map_path: str,
+                 ghost_output_content: str = ""):
+        """Log a hide operation."""
+        if not self._enabled:
+            return
+
+        entry = {
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "action": "hide",
+            "user": getpass.getuser(),
+            "hostname": platform.node(),
+            "source_files": source_files,
+            "scrub_level": scrub_level,
+            "function_isolated": function_isolated,
+            "symbols_scrubbed": symbols_scrubbed,
+            "literals_scrubbed": literals_scrubbed,
+            "literals_flagged": literals_flagged,
+            "literals_kept": literals_kept,
+            "comments_stripped": comments_stripped,
+            "warnings": [w.get("type", str(w)) for w in warnings],
+            "warning_count": len(warnings),
+            "ghost_output_hash": (
+                _hash_content(ghost_output_content) if ghost_output_content
+                else _hash_file(ghost_output_path)
+            ),
+            "map_hash": _hash_file(map_path),
+        }
+
+        self._write(entry)
+
+    def log_reveal(self, input_file: str, map_file: str,
+                   mode: str, symbols_restored: int,
+                   new_symbols: list[str],
+                   new_dependencies: list[str],
+                   annotations_count: int,
+                   confidence: str, confidence_score: int,
+                   output_path: str):
+        """Log a reveal operation."""
+        if not self._enabled:
+            return
+
+        entry = {
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "action": "reveal",
+            "user": getpass.getuser(),
+            "hostname": platform.node(),
+            "input_file": input_file,
+            "map_used": map_file,
+            "mode": mode,
+            "symbols_restored": symbols_restored,
+            "new_symbols_detected": len(new_symbols),
+            "new_symbols": new_symbols,
+            "new_dependencies": new_dependencies,
+            "annotations": annotations_count,
+            "confidence": confidence,
+            "confidence_score": confidence_score,
+            "output_hash": _hash_file(output_path),
+        }
+
+        self._write(entry)
+
+    def _write(self, entry: dict):
+        """Append a log entry to today's log file."""
+        os.makedirs(self._audit_dir, exist_ok=True)
+        today = datetime.now().strftime("%Y-%m-%d")
+        log_path = os.path.join(self._audit_dir, f"{today}.jsonl")
+
+        with open(log_path, "a") as f:
+            f.write(json.dumps(entry) + "\n")
+
+    def get_recent_entries(self, count: int = 10) -> list[dict]:
+        """Read the most recent audit log entries."""
+        entries = []
+        if not os.path.exists(self._audit_dir):
+            return entries
+
+        log_files = sorted(
+            [f for f in os.listdir(self._audit_dir) if f.endswith(".jsonl")],
+            reverse=True,
+        )
+
+        for log_file in log_files:
+            path = os.path.join(self._audit_dir, log_file)
+            with open(path) as f:
+                for line in f:
+                    line = line.strip()
+                    if line:
+                        entries.append(json.loads(line))
+            if len(entries) >= count:
+                break
+
+        return entries[-count:]