tunacode-cli 0.0.51__tar.gz → 0.0.53__tar.gz

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/CLAUDE.md

@@ -1,22 +1,17 @@
 # CLAUDE.md
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+#Enviroment
 
-## Commands
-
-### Development Commands
-
-```bash
-# Install development environment (recommended approach)
-./scripts/setup_dev_env.sh    # Creates fresh venv, installs deps, verifies setup
+Python3.10+
+venv must always be used
+follow modern python coding standards
+commit frequently with well documented messages
 
-# You must always follow the agent tooling workflow specified in agent_tools_prompt.xml
-
-When the directory "llm-agent-tools" exists, you MUST use this tooling flow and will be penalized if you don't:
+## Commands
 
-🚀 Available Tools:
+ Available Tools:
 1. scratchpad-multi.sh - Task tracking with multi-agent support (use --agent <name> for agent-specific work)
-2. knowledge.sh - Knowledge base with private/shared storage (use --agent <name> for agent-specific work) 
+2. knowledge.sh - Knowledge base with private/shared storage (use --agent <name> for agent-specific work)
 3. codemap.sh - Lightweight code intelligence for instant roadmaps
 4. context.sh - Context gathering for debugging issues
 5. researcher.sh - Online research and multimodal analysis via OpenRouter API
@@ -33,11 +28,7 @@ For new feature YOU MUST folow this flow
 - **Rinse & repeat:** keep iterations small, commit only green code, and let the tests guard future changes.
 
 
-# Manual installation
-pip install -e ".[dev]"      # Install in editable mode with dev dependencies
-pip install pytest-asyncio   # Additional test dependency
-
-# Run linting (black, isort, flake8)
+# Run linting (ruff)
 make lint
 
 # Run tests
@@ -60,13 +51,7 @@ make clean
 make run                     # Or: python -m tunacode
 ```
 
-### Version Management
-
-When updating versions, modify both:
-
-- `pyproject.toml`: version field
-- `src/tunacode/constants.py`: VERSION constant
-
+#
 ## Architecture
 
 TunaCode is a CLI tool that provides an AI-powered coding assistant using pydantic-ai. Key architectural decisions:
@@ -137,7 +122,6 @@ Modular setup with validation steps:
 - Output formatting via `rich` library
 - Tool confirmations show diffs for file operations
 - Spinner during agent processing
-- Optional Textual UI bridge (`cli/textual_app.py`, `cli/textual_bridge.py`)
 
 ## Testing
 
@@ -148,29 +132,7 @@ Modular setup with validation steps:
 - Characterization tests for capturing existing behavior
 - Async tests using `@pytest.mark.asyncio`
 
-### Test Markers
-
-- `@pytest.mark.slow` - Long-running tests
-- `@pytest.mark.integration` - Integration tests
-- `@pytest.mark.asyncio` - Async test functions
-
-### Running Tests
 
-```bash
-# Skip slow tests during development
-pytest -m "not slow"
-
-# Run only characterization tests
-pytest tests/test_characterization_*.py
-
-# Run with verbose output
-pytest -v
-
-# Run with coverage report
-pytest --cov=tunacode --cov-report=html
-```
-
-## Configuration
 
 ### User Configuration
 
@@ -186,21 +148,6 @@ Location: `~/.config/tunacode.json`
 }
 ```
 
-### Project Guide
-
-Location: `TUNACODE.md` in project root
-
-- Project-specific context for the AI assistant
-- Loaded automatically when present
-- Can include codebase conventions, architecture notes
-
-### Linting Configuration
-
-`.flake8` settings:
-
-- Max line length: 120
-- Ignores: E203, W503, E704 (Black compatibility)
-- Excludes: venv, build, dist directories
 
 ## Key Design Patterns
 
@@ -227,29 +174,3 @@ Location: `TUNACODE.md` in project root
 - Grep tool uses fast-glob prefiltering with MAX_GLOB limit
 - 3-second deadline for first match in searches
 - Background task management for non-blocking operations
-
-### Safety Features
-
-- No automatic git commits
-- File operations require explicit confirmation (unless in yolo mode)
-- Encourages git branches for experiments: `/branch <name>`
-- Git safety checks during setup
-
-Follow this code styling
-
-| #   | Rule                                           | One-line purpose                                                                                     |
-| --- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
-| 1   | **Guard Clause**                               | Flatten nested conditionals by returning early, so pre-conditions are explicit                       |
-| 2   | **Delete Dead Code**                           | If it’s never executed, delete it – that’s what VCS is for                                           |
-| 3   | **Normalize Symmetries**                       | Make identical things look identical and different things look different for faster pattern-spotting |
-| 4   | **New Interface, Old Implementation**          | Write the interface you wish existed; delegate to the old one for now                                |
-| 5   | **Reading Order**                              | Re-order elements so a reader meets ideas in the order they need them                                |
-| 6   | **Cohesion Order**                             | Cluster coupled functions/files so related edits sit together                                        |
-| 7   | **Move Declaration & Initialization Together** | Keep a variable’s birth and first value adjacent for comprehension & dependency safety               |
-| 8   | **Explaining Variable**                        | Extract a sub-expression into a well-named variable to record intent                                 |
-| 9   | **Explaining Constant**                        | Replace magic literals with symbolic constants that broadcast meaning                                |
-| 10  | **Explicit Parameters**                        | Split a routine so all inputs are passed openly, banishing hidden state or maps                      |
-
-## Task Master AI Instructions
-**Import Task Master's development workflow commands and guidelines, treat as if import is in the main CLAUDE.md file.**
-@./.taskmaster/CLAUDE.md

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/MANIFEST.in

@@ -16,4 +16,4 @@ recursive-include tests *.py
 global-exclude *.pyc
 global-exclude __pycache__
 global-exclude *.so
-global-exclude *.egg-info
+global-exclude *.egg-info

{tunacode_cli-0.0.51/src/tunacode_cli.egg-info → tunacode_cli-0.0.53}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tunacode-cli
-Version: 0.0.51
+Version: 0.0.53
 Summary: Your agentic CLI developer.
 Author-email: larock22 <noreply@github.com>
 License: MIT
@@ -35,6 +35,10 @@ Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: pytest-asyncio; extra == "dev"
 Requires-Dist: textual-dev; extra == "dev"
 Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: vulture>=2.7; extra == "dev"
+Requires-Dist: unimport>=1.0.0; extra == "dev"
+Requires-Dist: autoflake>=2.0.0; extra == "dev"
+Requires-Dist: dead>=1.5.0; extra == "dev"
 Dynamic: license-file
 
 # TunaCode CLI
@@ -175,3 +179,144 @@ _Note: While the tool is fully functional, we're focusing on stability and core
 ---
 
 MIT License - see [LICENSE](LICENSE) file
+
+hello from tuna world
+
+hello world
+
+## Getting Started
+
+### Prerequisites
+
+Before you begin, ensure you have the following installed:
+
+- Python 3.10 or higher
+- Git
+
+### Installation
+
+To install TunaCode, you can use one of the following methods:
+
+```bash
+# Option 1: One-line install (Linux/macOS)
+wget -qO- https://raw.githubusercontent.com/alchemiststudiosDOTai/tunacode/master/scripts/install_linux.sh | bash
+
+# Option 2: pip install
+pip install tunacode-cli
+```
+
+### Development Installation
+
+For developers who want to contribute to TunaCode:
+
+```bash
+# Clone the repository
+git clone https://github.com/alchemiststudiosDOTai/tunacode.git
+cd tunacode
+
+# Quick setup (recommended)
+./scripts/setup_dev_env.sh
+
+# Or manual setup
+python3 -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+pip install -e ".[dev]"
+
+# Verify installation
+python -m tunacode --version
+```
+
+See [Development Guide](docs/DEVELOPMENT.md) for detailed instructions.
+
+### Configuration
+
+Choose your AI provider and set your API key:
+
+```bash
+# OpenAI
+tunacode --model "openai:gpt-4o" --key "sk-your-openai-key"
+
+# Anthropic Claude
+tunacode --model "anthropic:claude-3.5-sonnet" --key "sk-ant-your-anthropic-key"
+
+# OpenRouter (100+ models)
+tunacode --model "openrouter:openai/gpt-4o" --key "sk-or-your-openrouter-key"
+```
+
+Your config is saved to `~/.config/tunacode.json` (edit directly with `nvim ~/.config/tunacode.json`)
+
+### Recommended Models
+
+Based on extensive testing, these models provide the best performance:
+
+- `google/gemini-2.5-pro` - Excellent for complex reasoning
+- `openai/gpt-4.1` - Strong general-purpose model
+- `deepseek/deepseek-r1-0528` - Great for code generation
+- `openai/gpt-4.1-mini` - Fast and cost-effective
+- `anthropic/claude-4-sonnet-20250522` - Superior context handling
+
+_Note: Formal evaluations coming soon. Any model can work, but these have shown the best results in practice._
+
+## Usage
+
+### Starting TunaCode
+
+```bash
+tunacode
+```
+
+### Basic Commands
+
+| Command                  | Description            |
+| ------------------------ | ---------------------- |
+| `/help`                  | Show all commands      |
+| `/model <provider:name>` | Switch model           |
+| `/clear`                 | Clear message history  |
+| `/compact`               | Summarize conversation |
+| `/branch <name>`         | Create Git branch      |
+| `/yolo`                  | Skip confirmations     |
+| `!<command>`             | Run shell command      |
+| `exit`                   | Exit TunaCode          |
+
+## Performance
+
+TunaCode leverages parallel execution for read-only operations, achieving **3x faster** file operations:
+
+![Parallel Execution Performance](docs/assets/parrelel_work_3x.png)
+
+Multiple file reads, directory listings, and searches execute concurrently using async I/O, making code exploration significantly faster.
+
+## Features in Development
+
+- **Streaming UI**: Currently working on implementing streaming responses for better user experience
+- **Bug Fixes**: Actively addressing issues - please report any bugs you encounter!
+
+_Note: While the tool is fully functional, we're focusing on stability and core features before optimizing for speed._
+
+## Safety First
+
+⚠️ **Important**: TunaCode can modify your codebase. Always:
+
+- Use Git branches before making changes
+- Review file modifications before confirming
+- Keep backups of important work
+
+## Documentation
+
+- [**Features**](docs/FEATURES.md) - All features, tools, and commands
+- [**Advanced Configuration**](docs/ADVANCED-CONFIG.md) - Provider setup, MCP, customization
+- [**Architecture**](docs/ARCHITECTURE.md) - Source code organization and design
+- [**Development**](docs/DEVELOPMENT.md) - Contributing and development setup
+- [**Troubleshooting**](docs/TROUBLESHOOTING.md) - Common issues and solutions
+
+## Links
+
+- [PyPI Package](https://pypi.org/project/tunacode-cli/)
+- [GitHub Repository](https://github.com/alchemiststudiosDOTai/tunacode)
+- [Report Issues](https://github.com/alchemiststudiosDOTai/tunacode/issues)
+
+---
+
+MIT License - see [LICENSE](LICENSE) file
+# Test
+# Test

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/README.md

@@ -136,3 +136,144 @@ _Note: While the tool is fully functional, we're focusing on stability and core
 ---
 
 MIT License - see [LICENSE](LICENSE) file
+
+hello from tuna world
+
+hello world
+
+## Getting Started
+
+### Prerequisites
+
+Before you begin, ensure you have the following installed:
+
+- Python 3.10 or higher
+- Git
+
+### Installation
+
+To install TunaCode, you can use one of the following methods:
+
+```bash
+# Option 1: One-line install (Linux/macOS)
+wget -qO- https://raw.githubusercontent.com/alchemiststudiosDOTai/tunacode/master/scripts/install_linux.sh | bash
+
+# Option 2: pip install
+pip install tunacode-cli
+```
+
+### Development Installation
+
+For developers who want to contribute to TunaCode:
+
+```bash
+# Clone the repository
+git clone https://github.com/alchemiststudiosDOTai/tunacode.git
+cd tunacode
+
+# Quick setup (recommended)
+./scripts/setup_dev_env.sh
+
+# Or manual setup
+python3 -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+pip install -e ".[dev]"
+
+# Verify installation
+python -m tunacode --version
+```
+
+See [Development Guide](docs/DEVELOPMENT.md) for detailed instructions.
+
+### Configuration
+
+Choose your AI provider and set your API key:
+
+```bash
+# OpenAI
+tunacode --model "openai:gpt-4o" --key "sk-your-openai-key"
+
+# Anthropic Claude
+tunacode --model "anthropic:claude-3.5-sonnet" --key "sk-ant-your-anthropic-key"
+
+# OpenRouter (100+ models)
+tunacode --model "openrouter:openai/gpt-4o" --key "sk-or-your-openrouter-key"
+```
+
+Your config is saved to `~/.config/tunacode.json` (edit directly with `nvim ~/.config/tunacode.json`)
+
+### Recommended Models
+
+Based on extensive testing, these models provide the best performance:
+
+- `google/gemini-2.5-pro` - Excellent for complex reasoning
+- `openai/gpt-4.1` - Strong general-purpose model
+- `deepseek/deepseek-r1-0528` - Great for code generation
+- `openai/gpt-4.1-mini` - Fast and cost-effective
+- `anthropic/claude-4-sonnet-20250522` - Superior context handling
+
+_Note: Formal evaluations coming soon. Any model can work, but these have shown the best results in practice._
+
+## Usage
+
+### Starting TunaCode
+
+```bash
+tunacode
+```
+
+### Basic Commands
+
+| Command                  | Description            |
+| ------------------------ | ---------------------- |
+| `/help`                  | Show all commands      |
+| `/model <provider:name>` | Switch model           |
+| `/clear`                 | Clear message history  |
+| `/compact`               | Summarize conversation |
+| `/branch <name>`         | Create Git branch      |
+| `/yolo`                  | Skip confirmations     |
+| `!<command>`             | Run shell command      |
+| `exit`                   | Exit TunaCode          |
+
+## Performance
+
+TunaCode leverages parallel execution for read-only operations, achieving **3x faster** file operations:
+
+![Parallel Execution Performance](docs/assets/parrelel_work_3x.png)
+
+Multiple file reads, directory listings, and searches execute concurrently using async I/O, making code exploration significantly faster.
+
+## Features in Development
+
+- **Streaming UI**: Currently working on implementing streaming responses for better user experience
+- **Bug Fixes**: Actively addressing issues - please report any bugs you encounter!
+
+_Note: While the tool is fully functional, we're focusing on stability and core features before optimizing for speed._
+
+## Safety First
+
+⚠️ **Important**: TunaCode can modify your codebase. Always:
+
+- Use Git branches before making changes
+- Review file modifications before confirming
+- Keep backups of important work
+
+## Documentation
+
+- [**Features**](docs/FEATURES.md) - All features, tools, and commands
+- [**Advanced Configuration**](docs/ADVANCED-CONFIG.md) - Provider setup, MCP, customization
+- [**Architecture**](docs/ARCHITECTURE.md) - Source code organization and design
+- [**Development**](docs/DEVELOPMENT.md) - Contributing and development setup
+- [**Troubleshooting**](docs/TROUBLESHOOTING.md) - Common issues and solutions
+
+## Links
+
+- [PyPI Package](https://pypi.org/project/tunacode-cli/)
+- [GitHub Repository](https://github.com/alchemiststudiosDOTai/tunacode)
+- [Report Issues](https://github.com/alchemiststudiosDOTai/tunacode/issues)
+
+---
+
+MIT License - see [LICENSE](LICENSE) file
+# Test
+# Test

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "tunacode-cli"
 
-version = "0.0.51"
+version = "0.0.53"
 description = "Your agentic CLI developer."
 keywords = ["cli", "agent", "development", "automation"]
 readme = "README.md"
@@ -46,6 +46,10 @@ dev = [
     "pytest-asyncio",
     "textual-dev",
     "pre-commit",
+    "vulture>=2.7",
+    "unimport>=1.0.0",
+    "autoflake>=2.0.0",
+    "dead>=1.5.0",
 ]
 
 [project.urls]
@@ -77,6 +81,7 @@ exclude = [
     "build",
     "dist",
     "venv",
+    "vulture_whitelist.py",
 ]
 
 [tool.vulture]
@@ -87,13 +92,13 @@ exclude = ["venv/", "build/", "dist/", ".git/", "__pycache__/", "*.egg-info/"]
 ignore_names = [
     # TYPE_CHECKING imports
     "ReadStream",
-    "WriteStream", 
+    "WriteStream",
     "StateManager",
     "ModelRequest",
     "CommandRegistry",
     # Pytest fixtures
     "caplog",
-    "temp_workspace", 
+    "temp_workspace",
     "setup_test_environment",
     "excinfo",
     # Common patterns
@@ -110,3 +115,17 @@ ignore_names = [
     "style_dict",  # Style.from_dict parameter
     "style_str",  # get_attrs_for_style_str parameter
 ]
+
+[tool.bandit]
+# Skip low-severity warnings for subprocess and assert statements
+skips = ["B404", "B603", "B101", "B607", "B110", "B324", "B103", "B604", "B602", "B108"]
+# B404: import subprocess
+# B603: subprocess without shell=True
+# B101: assert statements
+# B607: start process with partial path
+# B110: try/except/pass
+# B324: hashlib (SHA1 for non-security fingerprinting)
+# B103: chmod permissions (needed for template dirs)
+# B604: shell=True (validated usage in REPL)
+# B602: subprocess with shell=True (security utils)
+# B108: hardcoded tmp paths (test fixtures)

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/src/tunacode/cli/commands/base.py

@@ -44,12 +44,12 @@ class Command(ABC):
         return CommandCategory.SYSTEM
 
     @abstractmethod
-    async def execute(self, args: CommandArgs, context: CommandContext) -> CommandResult:
+    async def execute(self, _args: CommandArgs, context: CommandContext) -> CommandResult:
         """
         Execute the command.
 
         Args:
-            args: Command arguments (excluding the command name)
+            _args: Command arguments (excluding the command name)
             context: Execution context with state and config
 
         Returns:

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/src/tunacode/cli/commands/implementations/__init__.py

@@ -12,7 +12,13 @@ from .debug import (
 )
 from .development import BranchCommand, InitCommand
 from .model import ModelCommand
-from .system import ClearCommand, HelpCommand, RefreshConfigCommand, StreamingCommand, UpdateCommand
+from .system import (
+    ClearCommand,
+    HelpCommand,
+    RefreshConfigCommand,
+    StreamingCommand,
+    UpdateCommand,
+)
 from .todo import TodoCommand
 
 __all__ = [

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/src/tunacode/cli/commands/implementations/conversation.py

@@ -40,7 +40,7 @@ class CompactCommand(SimpleCommand):
         result = await process_request(
             summary_prompt,
             context.state_manager,
-            output=False,  # We'll handle the output ourselves
+            False,  # We'll handle the output ourselves
         )
 
         # Extract summary text from result

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/src/tunacode/cli/commands/implementations/debug.py

@@ -169,7 +169,7 @@ class ParseToolsCommand(SimpleCommand):
                         # Create tool callback
                         from tunacode.cli.repl import _tool_handler
 
-                        def tool_callback_with_state(part, node):
+                        def tool_callback_with_state(part, _node):
                             return _tool_handler(part, context.state_manager)
 
                         try:

{tunacode_cli-0.0.51 → tunacode_cli-0.0.53}/src/tunacode/cli/commands/implementations/development.py

@@ -72,6 +72,9 @@ If there are Cursor rules (in .cursor/rules/ or .cursorrules) or Copilot rules (
 make sure to include them."""
 
         # Call the agent to analyze and create/update the file
-        await context.process_request(prompt, context.state_manager)
+        if context.process_request:
+            await context.process_request(
+                prompt, context.state_manager.session.current_model, context.state_manager
+            )
 
         return None