codigest 0.3.0__tar.gz

codigest-0.3.0/.github/workflows/main.yml

@@ -0,0 +1,30 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+jobs:
+  pypi-publish:
+    name: Build and publish Python distribution to PyPI
+    runs-on: ubuntu-latest
+    environment: github
+    permissions:
+      id-token: write
+      contents: read
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+
+    - name: Set up Python
+      run: uv python install 3.14
+
+    - name: Build package
+      run: uv build
+
+    - name: Publish package distributions to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

codigest-0.3.0/.github/workflows/publish.yml

@@ -0,0 +1,75 @@
+name: Publish Python distributions to PyPI and GitHub Pages
+
+on:
+  push:
+    tags:
+      - 'v*'  # v0.3.0 태그 푸시 시 배포 실행
+    # branches:
+    #   - main  # main 브랜치 푸시 시 문서 배포 실행 (옵션)
+
+jobs:
+  build-n-publish:
+    name: Build and publish Python distributions to PyPI
+    runs-on: ubuntu-latest
+    # v* 태그일 때만 실행
+    if: startsWith(github.ref, 'refs/tags/v')
+    environment: release
+    permissions:
+      id-token: write  # Trusted Publishing을 위한 필수 권한
+      contents: read
+    
+    steps:
+    - uses: actions/checkout@v4
+    
+    # [변경] uv 설치 (가장 빠르고 확실한 방법)
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+    
+    # [변경] Python 3.14 설정 (uv 이용)
+    - name: Set up Python
+      run: uv python install 3.14
+    
+    # [변경] 의존성 설치 및 빌드 (uv build 하나로 해결)
+    - name: Build package
+      run: uv build
+    
+    # PyPI 배포 (기존 형식 유지)
+    - name: Publish package distributions to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+
+  deploy-docs:
+    name: Build and deploy Sphinx docs to GitHub Pages
+    runs-on: ubuntu-latest
+    if: github.ref == 'refs/heads/main'
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Set up Python
+        run: uv python install 3.14
+
+      - name: Install Python and Sphinx dependencies
+        run: |
+          uv pip install --system --upgrade pip
+          if [ -f docs/requirements.txt ]; then uv pip install --system -r docs/requirements.txt; fi
+
+      - name: Build HTML docs with Sphinx
+        run: |
+          if [ -d "docs" ]; then
+            sphinx-build -b html docs/source docs/html
+            touch docs/html/.nojekyll
+          else
+            echo "No docs folder found, skipping build."
+            mkdir -p docs/html
+            touch docs/html/.nojekyll
+          fi
+
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: docs/html

codigest-0.3.0/.gitignore

@@ -0,0 +1,87 @@
+# --------------------------------------------------------------------
+# Python Core & Bytecode
+# --------------------------------------------------------------------
+__pycache__/
+*.py[cod]
+*$py.class
+
+# --------------------------------------------------------------------
+# Virtual Environments (uv / venv)
+# --------------------------------------------------------------------
+.venv/
+venv/
+env/
+ENV/
+
+# --------------------------------------------------------------------
+# Distribution / Build Artifacts
+# --------------------------------------------------------------------
+build/
+dist/
+wheels/
+*.egg-info/
+.eggs/
+*.egg
+MANIFEST
+
+# --------------------------------------------------------------------
+# Tooling Caches & Logs
+# --------------------------------------------------------------------
+# Ruff
+.ruff_cache/
+
+# MyPy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pytest / Coverage
+.pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+*.cover
+
+# Log files
+*.log
+
+# --------------------------------------------------------------------
+# Environment Variables & Secrets
+# --------------------------------------------------------------------
+.env
+.env.local
+.secrets
+
+# --------------------------------------------------------------------
+# IDE & Editor Settings
+# --------------------------------------------------------------------
+# VS Code
+.vscode/
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+
+# JetBrains / PyCharm
+.idea/
+
+# macOS
+.DS_Store
+
+# --------------------------------------------------------------------
+# Codigest Project Specifics
+# --------------------------------------------------------------------
+# Artifact directory (stores config, prompts, but often ignored if local-only)
+# You might want to commit .codigest/config.toml and prompts.toml, 
+# but ignore the output snapshots.
+# For now, following your previous pattern:
+.codigest/
+
+# Default output filenames (if generated in root)
+snapshot.xml
+digest.xml
+changes.diff
+tree.txt
+
+# Temporary test outputs
+test_output/

codigest-0.3.0/.python-version

@@ -0,0 +1 @@
+3.14

codigest-0.3.0/PKG-INFO

@@ -0,0 +1,145 @@
+Metadata-Version: 2.4
+Name: codigest
+Version: 0.3.0
+Summary: Human-Centered Codebase Context Manager for LLMs
+Project-URL: Homepage, https://github.com/SJB777/codigest
+Project-URL: Repository, https://github.com/SJB777/codigest
+Project-URL: Issues, https://github.com/SJB777/codigest/issues
+Author-email: Codigest Team <sngd024@google.com>
+License: MIT
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Utilities
+Requires-Python: >=3.14
+Requires-Dist: loguru
+Requires-Dist: pathspec
+Requires-Dist: pyperclip
+Requires-Dist: rich
+Requires-Dist: tomli-w
+Requires-Dist: typer
+Description-Content-Type: text/markdown
+
+# Codigest
+
+Codigest is a CLI tool designed to extract, structure, and track the context of your codebase for Large Language Models (LLMs).
+
+Unlike simple copy-paste tools, Codigest employs a **Context Anchor** system (Shadow Git) to track changes locally without polluting your main version control history. It also features **Semantic Analysis** to detect structural changes in your code.
+
+## Core Philosophy
+
+* **Read-Only & Safe**: Codigest never modifies your source code. It only reads, analyzes, and formats context.
+* **Context-Aware**: Instead of dumping raw text, it structures code into XML snapshots designed for LLM comprehension.
+* **Session-Based Tracking**: It maintains an internal anchor to track "work-in-progress" changes independently of your Git commits.
+* **Python 3.14 Native**: Built using modern Python features including PEP 750 Tag Strings for safe XML generation.
+
+## Installation
+
+Requires **Python 3.14+**.
+
+```bash
+# Install via uv
+git clone https://github.com/SJB7777/codigest.git
+cd codigest
+uv tool install .
+````
+
+## Workflow & Commands
+
+### 1\. Initialization
+
+Sets up the `.codigest` directory and captures the initial baseline anchor.
+
+```bash
+codigest init
+```
+
+### 2\. Full Context Snapshot (`scan`)
+
+Scans the entire codebase and generates a structured XML snapshot.
+
+  * **Output:** `.codigest/snapshot.xml`
+  * **Use Case:** Providing the LLM with the full project context at the start of a session.
+  * **Side Effect:** Updates the internal Context Anchor to the current state.
+
+```bash
+codigest scan --m " Python 3.14 project. Do NOT use typing. List/Dict."
+```
+
+### 3\. Incremental Changes (`diff`)
+
+Tracks text-based changes between the last `scan` and the current working tree.
+
+  * **Output:** `.codigest/changes.diff`
+  * **Use Case:** "I modified 3 files. Here is exactly what changed since the last snapshot."
+  * **Note:** This is based on the internal Shadow Git, not your project's Git history.
+
+```bash
+codigest diff
+```
+
+### 4\. Semantic Analysis (`semdiff`)
+
+Analyzes **structural changes** (AST-based) rather than line-by-line text differences.
+
+  * **Output:** `.codigest/semdiff.xml`
+  * **Use Case:** "I refactored the API. Show me which functions were added, removed, or had their signatures changed."
+  * **Benefit:** Significantly reduces token usage compared to raw diffs by ignoring formatting/comment changes.
+
+```bash
+codigest semdiff
+```
+
+### 5\. Architecture Digest (`digest`)
+
+Generates a high-level outline of the project structure (Classes, Functions, Methods only).
+
+  * **Output:** `.codigest/digest.xml`
+  * **Use Case:** "Don't read the implementation details. Just understand the class hierarchy and available methods."
+
+<!-- end list -->
+
+```bash
+codigest digest
+```
+
+## Configuration
+
+You can customize behavior in `.codigest/config.toml`.
+
+```toml
+[filter]
+# Target extensions
+extensions = [".py", ".ts", ".rs", ".md", ".json"]
+
+# Exclude patterns (Gitignore syntax)
+exclude_patterns = [
+    "*.lock",
+    "tests/data/",
+    "legacy_code/"
+]
+
+[output]
+format = "xml"
+```
+
+## Architecture Details
+
+**Context Anchor (Shadow Git)**
+Codigest maintains a hidden, lightweight Git repository inside `.codigest/anchor`.
+
+  * When you run `scan`, the current state is committed to this anchor.
+  * When you run `diff`, the tool compares your working directory against this anchor.
+  * When you run `semdiff`, the tool parses the AST of the anchor version and the current version to detect logical drifts.
+
+**Safety Mechanisms**
+
+  * **structure-aware dedent:** Ensures XML tags are perfectly aligned regardless of code indentation.
+  * **Automatic Exclusion:** Self-referential files (`.codigest/`) are automatically ignored to prevent recursion loops.
+
+## License
+
+MIT License

codigest-0.3.0/README.md

@@ -0,0 +1,120 @@
+# Codigest
+
+Codigest is a CLI tool designed to extract, structure, and track the context of your codebase for Large Language Models (LLMs).
+
+Unlike simple copy-paste tools, Codigest employs a **Context Anchor** system (Shadow Git) to track changes locally without polluting your main version control history. It also features **Semantic Analysis** to detect structural changes in your code.
+
+## Core Philosophy
+
+* **Read-Only & Safe**: Codigest never modifies your source code. It only reads, analyzes, and formats context.
+* **Context-Aware**: Instead of dumping raw text, it structures code into XML snapshots designed for LLM comprehension.
+* **Session-Based Tracking**: It maintains an internal anchor to track "work-in-progress" changes independently of your Git commits.
+* **Python 3.14 Native**: Built using modern Python features including PEP 750 Tag Strings for safe XML generation.
+
+## Installation
+
+Requires **Python 3.14+**.
+
+```bash
+# Install via uv
+git clone https://github.com/SJB7777/codigest.git
+cd codigest
+uv tool install .
+````
+
+## Workflow & Commands
+
+### 1\. Initialization
+
+Sets up the `.codigest` directory and captures the initial baseline anchor.
+
+```bash
+codigest init
+```
+
+### 2\. Full Context Snapshot (`scan`)
+
+Scans the entire codebase and generates a structured XML snapshot.
+
+  * **Output:** `.codigest/snapshot.xml`
+  * **Use Case:** Providing the LLM with the full project context at the start of a session.
+  * **Side Effect:** Updates the internal Context Anchor to the current state.
+
+```bash
+codigest scan --m " Python 3.14 project. Do NOT use typing. List/Dict."
+```
+
+### 3\. Incremental Changes (`diff`)
+
+Tracks text-based changes between the last `scan` and the current working tree.
+
+  * **Output:** `.codigest/changes.diff`
+  * **Use Case:** "I modified 3 files. Here is exactly what changed since the last snapshot."
+  * **Note:** This is based on the internal Shadow Git, not your project's Git history.
+
+```bash
+codigest diff
+```
+
+### 4\. Semantic Analysis (`semdiff`)
+
+Analyzes **structural changes** (AST-based) rather than line-by-line text differences.
+
+  * **Output:** `.codigest/semdiff.xml`
+  * **Use Case:** "I refactored the API. Show me which functions were added, removed, or had their signatures changed."
+  * **Benefit:** Significantly reduces token usage compared to raw diffs by ignoring formatting/comment changes.
+
+```bash
+codigest semdiff
+```
+
+### 5\. Architecture Digest (`digest`)
+
+Generates a high-level outline of the project structure (Classes, Functions, Methods only).
+
+  * **Output:** `.codigest/digest.xml`
+  * **Use Case:** "Don't read the implementation details. Just understand the class hierarchy and available methods."
+
+<!-- end list -->
+
+```bash
+codigest digest
+```
+
+## Configuration
+
+You can customize behavior in `.codigest/config.toml`.
+
+```toml
+[filter]
+# Target extensions
+extensions = [".py", ".ts", ".rs", ".md", ".json"]
+
+# Exclude patterns (Gitignore syntax)
+exclude_patterns = [
+    "*.lock",
+    "tests/data/",
+    "legacy_code/"
+]
+
+[output]
+format = "xml"
+```
+
+## Architecture Details
+
+**Context Anchor (Shadow Git)**
+Codigest maintains a hidden, lightweight Git repository inside `.codigest/anchor`.
+
+  * When you run `scan`, the current state is committed to this anchor.
+  * When you run `diff`, the tool compares your working directory against this anchor.
+  * When you run `semdiff`, the tool parses the AST of the anchor version and the current version to detect logical drifts.
+
+**Safety Mechanisms**
+
+  * **structure-aware dedent:** Ensures XML tags are perfectly aligned regardless of code indentation.
+  * **Automatic Exclusion:** Self-referential files (`.codigest/`) are automatically ignored to prevent recursion loops.
+
+## License
+
+MIT License

codigest-0.3.0/pyproject.toml

@@ -0,0 +1,38 @@
+[project]
+name = "codigest"
+version = "0.3.0"
+description = "Human-Centered Codebase Context Manager for LLMs"
+authors = [{name = "Codigest Team", email = "sngd024@google.com"}]
+readme = "README.md"
+requires-python = ">=3.14"
+license = { text = "MIT" }
+dependencies = [
+    "typer",
+    "rich",
+    "loguru",
+    "pathspec",
+    "pyperclip",
+    "tomli-w",
+]
+
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.14",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Utilities",
+    "Intended Audience :: Developers",
+]
+
+[project.urls]
+Homepage = "https://github.com/SJB777/codigest"
+Repository = "https://github.com/SJB777/codigest"
+Issues = "https://github.com/SJB777/codigest/issues"
+
+[project.scripts]
+codigest = "codigest.main:app"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

codigest-0.3.0/src/codigest/commands/diff.py

@@ -0,0 +1,84 @@
+import typer
+import pyperclip
+from pathlib import Path
+from rich.console import Console
+from rich.progress import Progress, SpinnerColumn, TextColumn
+
+from ..core import scanner, prompts, shadow
+from .scan import _load_config_filters 
+
+app = typer.Typer()
+console = Console()
+
+@app.callback(invoke_without_command=True)
+def handle(
+    copy: bool = typer.Option(True, help="Auto-copy to clipboard"),
+    save: bool = typer.Option(True, help="Save to .codigest/changes.diff"),
+    message: str = typer.Option("", "--message", "-m", help="Add specific instruction context"),
+):
+    """
+    [Context Update] Shows changes since the last 'codigest scan'.
+    Useful for updating LLM context without re-uploading everything.
+    """
+    root_path = Path.cwd()
+    anchor = shadow.ContextAnchor(root_path)
+    
+    # 1. Check Baseline Existence
+    last_update = anchor.get_last_update_time()
+    if last_update == "Never":
+        console.print("[yellow]⚠️  No scan history found.[/yellow]")
+        console.print("   Run [bold cyan]codigest scan[/bold cyan] first to establish a baseline.")
+        raise typer.Exit(1)
+
+    console.print(f"[dim]Checking changes since last scan ({last_update})...[/dim]")
+
+    # 2. Calculate Diff
+    with Progress(
+        SpinnerColumn(),
+        TextColumn("[bold blue]Analyzing changes...[/bold blue]"),
+        transient=True,
+        console=console
+    ) as progress:
+        task = progress.add_task("diff", total=None)
+        
+        # Load same filters as scan
+        extensions, extra_ignores = _load_config_filters(root_path)
+        
+        # Get current valid files (Working Tree)
+        current_files = scanner.scan_project(root_path, extensions, extra_ignores)
+        
+        # Compare Working Tree vs Anchor
+        diff_content = anchor.get_changes(current_files)
+        
+        progress.update(task, completed=100)
+
+    if not diff_content.strip():
+        console.print("[green]✨ No changes detected since last scan.[/green]")
+        return
+
+    # 3. Render
+    prompt_engine = prompts.get_engine(root_path)
+    try:
+        formatted_diff = prompt_engine.render(
+            "diff",
+            project_name=root_path.name,
+            context_message=f"Changes since last scan ({last_update})",
+            diff_content=diff_content,
+            instruction=message
+        )
+    except Exception:
+        # Fallback if template fails
+        formatted_diff = f"<diff>\n{diff_content}\n</diff>"
+
+    # 4. Output
+    console.print(f"[bold green]✔ Changes Detected![/bold green] ({len(formatted_diff)} chars)")
+    
+    if copy:
+        pyperclip.copy(formatted_diff)
+        console.print("[dim]📋 Copied to clipboard[/dim]")
+
+    if save:
+        out_path = root_path / ".codigest" / "changes.diff"
+        out_path.parent.mkdir(exist_ok=True)
+        out_path.write_text(formatted_diff, encoding="utf-8")
+        console.print(f"[dim]💾 Saved to {out_path}[/dim]")

codigest-0.3.0/src/codigest/commands/digest.py

@@ -0,0 +1,88 @@
+import typer
+import pyperclip
+from pathlib import Path
+from rich.console import Console
+from rich.progress import Progress, SpinnerColumn, TextColumn
+
+from ..core import scanner, structure, prompts, semdiff, tags, tokenizer
+
+# Reuse config loader
+from .scan import _load_config_filters 
+
+app = typer.Typer()
+console = Console()
+
+@app.callback(invoke_without_command=True)
+def handle(
+    target: Path = typer.Argument(Path.cwd(), help="Target directory"),
+    copy: bool = typer.Option(True, help="Auto-copy to clipboard"),
+    save: bool = typer.Option(True, help="Save to .codigest/digest.xml"),
+    message: str = typer.Option("", "--message", "-m", help="Add specific instruction"),
+):
+    """
+    [Architectural View] Summarizes the codebase structure (Classes/Functions only).
+    """
+    root_path = target.resolve()
+    
+    prompt_engine = prompts.get_engine(root_path)
+    extensions, extra_ignores = _load_config_filters(root_path)
+
+    with Progress(
+        SpinnerColumn(),
+        TextColumn("[bold blue]Digesting Architecture...[/bold blue]"),
+        transient=True,
+        console=console
+    ) as progress:
+        
+        task = progress.add_task("digest", total=None)
+        
+        files = scanner.scan_project(root_path, extensions, extra_ignores)
+        tree_str = structure.generate_ascii_tree(files, root_path)
+
+        summary_blocks = []
+        for file_path in files:
+            # Only summarize Python files via AST
+            if file_path.suffix in (".py", ".pyi"):
+                try:
+                    content = file_path.read_text(encoding="utf-8")
+                    summary = semdiff.summarize(content)
+                    
+                    if summary:
+                        rel_path = file_path.relative_to(root_path).as_posix()
+                        block = tags.xml(t"""
+                        <file path="{rel_path}">
+                        {summary}
+                        </file>
+                        """)
+                        summary_blocks.append(block)
+                except Exception:
+                    continue
+
+        summary_blob = "\n".join(summary_blocks)
+        
+        try:
+            digest_content = prompt_engine.render(
+                "digest",
+                project_name=root_path.name,
+                tree_structure=tree_str,
+                digest_content=summary_blob,
+                instruction=message
+            )
+        except Exception as e:
+            console.print(f"[red]❌ Rendering Failed:[/red] {e}")
+            raise typer.Exit(1)
+            
+        progress.update(task, completed=100)
+
+    token_count = tokenizer.estimate_tokens(digest_content)
+    console.print(f"[bold green]✔ Digest Generated![/bold green] ([bold cyan]~{token_count:,} Tokens[/bold cyan])")
+    
+    if copy:
+        pyperclip.copy(digest_content)
+        console.print("[dim]📋 Copied to clipboard[/dim]")
+    
+    if save:
+        out_path = root_path / ".codigest" / "digest.xml"
+        out_path.parent.mkdir(exist_ok=True)
+        out_path.write_text(digest_content, encoding="utf-8")
+        console.print(f"[dim]💾 Saved to {out_path}[/dim]")