devorch 0.1.2__py3-none-any.whl

devorch-0.1.2.dist-info/METADATA

@@ -0,0 +1,528 @@
+Metadata-Version: 2.4
+Name: devorch
+Version: 0.1.2
+Summary: Multi-provider AI coding assistant CLI with 13+ providers
+Project-URL: Homepage, https://github.com/Amanbig/DevOrch
+Project-URL: Repository, https://github.com/Amanbig/DevOrch
+Project-URL: Issues, https://github.com/Amanbig/DevOrch/issues
+Author-email: Aman <amanpreetsinghjhiwant@outlook.com>
+License: MIT
+Keywords: ai,anthropic,assistant,claude,cli,coding,copilot,deepseek,gemini,gpt,kimi,llm,llmstudio,mistral,openai,openrouter,together
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Requires-Dist: anthropic>=0.25.8
+Requires-Dist: duckduckgo-search>=6.0.0
+Requires-Dist: google-genai>=1.0.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: keyring>=25.0.0
+Requires-Dist: openai>=1.28.0
+Requires-Dist: prompt-toolkit>=3.0.0
+Requires-Dist: pydantic>=2.7.1
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: questionary>=2.0.0
+Requires-Dist: rich>=13.7.1
+Requires-Dist: typer>=0.12.3
+Provides-Extra: dev
+Requires-Dist: mypy>=1.10.0; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
+Requires-Dist: pytest-cov>=5.0.0; extra == 'dev'
+Requires-Dist: pytest>=8.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.4.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# DevOrch
+
+A multi-provider AI coding assistant CLI, similar to Claude Code and Gemini CLI.
+
+![DevOrch Banner](https://img.shields.io/badge/DevOrch-AI%20Coding%20Assistant-blue)
+![Python](https://img.shields.io/badge/Python-3.10+-green)
+![License](https://img.shields.io/badge/License-MIT-yellow)
+
+## Features
+
+- **13 AI Providers** - OpenAI, Anthropic, Gemini, Groq, Mistral, Together AI, OpenRouter, GitHub Copilot, DeepSeek, Kimi, Ollama, LM Studio, and Custom
+- **Custom Provider Support** - Connect to ANY OpenAI-compatible API (vLLM, TGI, llama.cpp, etc.)
+- **Dynamic Model Listing** - Fetches latest available models from provider APIs
+- **Secure API Key Storage** - Uses system keychain (Windows Credential Manager, macOS Keychain, Linux Secret Service)
+- **Session Persistence** - SQLite-based chat history with resume capability
+- **Powerful Tools** - Shell, terminal sessions, file operations, search, grep, code editing, and web access
+- **Interactive UI** - Arrow-key navigation for selections, syntax-highlighted output
+- **Permission System** - Configurable allow/deny rules with interactive prompts
+- **Terminal Session Management** - Run long-running servers and background processes
+- **Multiple Modes** - Plan mode, Auto mode, and Ask mode
+
+## Installation
+
+### Option 1: Install with pipx (Recommended)
+
+```bash
+# Install pipx if you don't have it
+pip install pipx
+
+# Install DevOrch
+pipx install devorch
+
+# DevOrch is now available globally
+devorch --help
+```
+
+### Option 2: Install with pip
+
+```bash
+pip install devorch
+```
+
+### Option 3: Install from source
+
+```bash
+# Clone the repository
+git clone https://github.com/Amanbig/DevOrch.git
+cd DevOrch
+
+# Install with pip
+pip install -e .
+```
+
+### Why pipx?
+
+- ✅ Isolated environment (no conflicts with other packages)
+- ✅ Available globally like `npm install -g`
+- ✅ Easy to uninstall: `pipx uninstall devorch`
+- ✅ Easy to upgrade: `pipx upgrade devorch`
+
+## Quick Start
+
+```bash
+# Start DevOrch (first run will show interactive setup)
+devorch
+
+# Or specify a provider
+devorch -p openai
+devorch -p anthropic
+devorch -p groq
+devorch -p local  # Ollama
+```
+
+## Interactive Onboarding
+
+On first run, DevOrch guides you through setup with an interactive UI:
+
+```
+╭─────────────────────────────────────────────────╮
+│ Welcome to DevOrch!                             │
+│                                                 │
+│ Let's set up your AI provider to get started.  │
+╰─────────────────────────────────────────────────╯
+
+? Select your AI provider: (Use arrow keys)
+ ❯ OpenAI (GPT-4o, GPT-4, etc.)
+   Anthropic (Claude Sonnet, Opus, etc.)
+   Google Gemini (Gemini Pro, Flash, etc.)
+   Groq (Ultra-fast Llama, Mixtral)
+   ──────────────
+   Ollama - Local (No API key needed)
+   LM Studio - Local (No API key needed)
+```
+
+## Usage
+
+### Interactive REPL
+
+```bash
+devorch                    # Start interactive session
+devorch -p groq            # Use specific provider
+devorch -m gpt-4o          # Use specific model
+devorch --resume abc123    # Resume a previous session
+```
+
+### Slash Commands
+
+| Command | Description |
+|---------|-------------|
+| `/help` | Show available commands |
+| `/mode` | Interactive mode selection (plan/auto/ask) |
+| `/model` | Interactive model selection |
+| `/provider` | Interactive provider switching |
+| `/models` | List available models for current provider |
+| `/providers` | List all available providers |
+| `/status` | Show current provider, model, and mode |
+| `/session` | Show current session info |
+| `/history` | Show conversation history |
+| `/clear` | Clear conversation history |
+| `/compact` | Summarize and compact history |
+| `/save` | Save conversation to file |
+| `/undo` | Undo last message |
+| `/tasks` | Show current task list |
+
+### Modes
+
+- **ASK** (default) - Asks before each tool execution
+- **AUTO** - Executes tools automatically (dangerous commands still blocked)
+- **PLAN** - Shows plan before executing, asks for approval
+
+Switch modes interactively:
+```
+? Select mode: (Use arrow keys)
+ ❯ PLAN - Shows plan before executing, asks for approval
+   AUTO - Executes tools automatically (trusted mode)
+   ASK - Asks before each tool execution (default)
+```
+
+## Tool Permissions
+
+DevOrch uses an interactive permission system with arrow-key navigation:
+
+```
+╭─────────── Permission Required ───────────╮
+│ Tool: shell                               │
+│ Command: npm create vite@latest           │
+╰───────────────────────────────────────────╯
+
+? Choose an action: (Use arrow keys)
+ ❯ Allow once
+   Allow for this session
+   Always allow (save to config)
+   Deny
+```
+
+## Tool Output Display
+
+Tool calls are displayed in a clean, compact format:
+
+```
+╭──────────── Shell ────────────╮
+│ npm create vite@latest my-app │
+╰───────────────────────────────╯
+
+╭─────────── Output ────────────╮
+│ STDOUT:                       │
+│ Scaffolding project in ./my-  │
+│ app                           │
+│ Done!                         │
+╰───────────────────────────────╯
+
+  > write 45 lines to src/App.tsx
+    ✓ Successfully wrote 45 lines to src/App.tsx
+
+  > read package.json
+    ✓ Read 32 lines
+```
+
+## New Provider Features
+
+### GitHub Copilot Integration
+
+Use your GitHub Copilot subscription to access multiple premium models:
+
+```bash
+# Get GitHub token with 'copilot' scope from:
+# https://github.com/settings/tokens
+
+export GITHUB_TOKEN=ghp_your_token
+
+# Use Copilot
+devorch -p github_copilot
+devorch -p github_copilot -m claude-3.5-sonnet
+```
+
+**Available models:** GPT-4o, GPT-4o-mini, Claude 3.5 Sonnet, o1-preview, o1-mini
+
+### DeepSeek AI
+
+Powerful reasoning and coding models from DeepSeek:
+
+```bash
+export DEEPSEEK_API_KEY=sk-...
+devorch -p deepseek -m deepseek-reasoner
+```
+
+**Models:** deepseek-chat, deepseek-coder, deepseek-reasoner (R1)
+
+### Kimi (Moonshot AI)
+
+Long context models with up to 128K tokens:
+
+```bash
+export MOONSHOT_API_KEY=sk-...
+devorch -p kimi -m moonshot-v1-128k
+```
+
+**Models:** moonshot-v1-8k, moonshot-v1-32k, moonshot-v1-128k
+
+### Custom Providers
+
+Connect to ANY OpenAI-compatible API:
+
+#### Self-Hosted vLLM
+
+```yaml
+# ~/.devorch/config.yaml
+providers:
+  my_vllm:
+    default_model: meta-llama/Meta-Llama-3-70B-Instruct
+    base_url: http://localhost:8000/v1
+```
+
+```bash
+# Start vLLM server
+python -m vllm.entrypoints.openai.api_server \
+    --model meta-llama/Meta-Llama-3-70B-Instruct \
+    --port 8000
+
+# Use it
+devorch -p my_vllm
+```
+
+#### Text Generation Inference (TGI)
+
+```yaml
+providers:
+  my_tgi:
+    default_model: mistralai/Mistral-7B-Instruct
+    base_url: http://localhost:8080/v1
+```
+
+#### llama.cpp Server
+
+```yaml
+providers:
+  llamacpp:
+    default_model: llama-3-8b
+    base_url: http://localhost:8080/v1
+```
+
+#### Private API Endpoint
+
+```yaml
+providers:
+  company_api:
+    default_model: custom-model-v1
+    base_url: https://api.company.com/v1
+    # Set CUSTOM_API_KEY environment variable
+```
+
+### Dynamic Model Listing
+
+All providers now fetch available models from their APIs automatically:
+
+```bash
+# List available models
+devorch models list -p deepseek
+devorch models list -p github_copilot
+devorch models list -p my_vllm
+```
+
+Models are fetched in real-time from provider APIs, so you always see the latest available models!
+
+## Configuration
+
+### API Keys
+
+```bash
+# Store API keys securely in system keyring
+devorch set-key openai
+devorch set-key anthropic
+devorch set-key groq
+devorch set-key github_copilot  # Uses GITHUB_TOKEN
+devorch set-key deepseek
+devorch set-key kimi
+
+# Or use environment variables
+export OPENAI_API_KEY=sk-...
+export ANTHROPIC_API_KEY=sk-ant-...
+export GOOGLE_API_KEY=...
+export GROQ_API_KEY=gsk_...
+export MISTRAL_API_KEY=...
+export OPENROUTER_API_KEY=sk-or-...
+export TOGETHER_API_KEY=...
+export GITHUB_TOKEN=ghp_...
+export DEEPSEEK_API_KEY=sk-...
+export MOONSHOT_API_KEY=sk-...
+```
+
+### View Configuration
+
+```bash
+devorch config
+```
+
+### Configuration File
+
+Create `~/.devorch/config.yaml` to configure providers:
+
+```yaml
+# Set default provider
+default_provider: openai
+
+# Configure each provider
+providers:
+  openai:
+    default_model: gpt-4o
+
+  anthropic:
+    default_model: claude-sonnet-4-20250514
+
+  github_copilot:
+    default_model: gpt-4o
+
+  deepseek:
+    default_model: deepseek-chat
+
+  kimi:
+    default_model: moonshot-v1-32k
+
+  # Custom providers
+  my_vllm:
+    default_model: meta-llama/Meta-Llama-3-70B-Instruct
+    base_url: http://localhost:8000/v1
+
+  company_api:
+    default_model: custom-model-v1
+    base_url: https://api.company.com/v1
+```
+
+**Note:** Don't put API keys in config files! Use environment variables or keyring.
+
+### Session Management
+
+```bash
+devorch sessions list           # List all sessions
+devorch sessions show <id>      # Show session details
+devorch sessions delete <id>    # Delete a session
+devorch sessions clear          # Delete all sessions
+```
+
+### Permissions
+
+```bash
+devorch permissions list                    # Show permissions
+devorch permissions set shell allow         # Always allow shell commands
+devorch permissions allow shell "git *"     # Allow git commands
+devorch permissions deny shell "rm -rf *"   # Block dangerous commands
+devorch permissions reset                   # Reset to defaults
+```
+
+## Supported Providers
+
+### Cloud Providers
+
+| Provider | Models | API Key | Notes |
+|----------|--------|---------|-------|
+| **OpenAI** | GPT-4o, GPT-4, o1-preview | `OPENAI_API_KEY` | Full support with tool calling |
+| **Anthropic** | Claude 4.5, Claude 3.5, Claude 3 | `ANTHROPIC_API_KEY` | Best for coding tasks |
+| **Google Gemini** | Gemini 2.0, 1.5 Pro/Flash | `GOOGLE_API_KEY` | 2M token context |
+| **Groq** | Llama 3.3, Mixtral, Gemma | `GROQ_API_KEY` | Ultra-fast inference |
+| **Mistral** | Large, Medium, Codestral | `MISTRAL_API_KEY` | Specialized for code |
+| **Together AI** | Llama 3, Mixtral, Qwen | `TOGETHER_API_KEY` | Open source models |
+| **OpenRouter** | 100+ models | `OPENROUTER_API_KEY` | Access many providers via one API |
+
+### Developer Tools
+
+| Provider | Models | API Key | Notes |
+|----------|--------|---------|-------|
+| **GitHub Copilot** ⭐ | GPT-4o, Claude 3.5, o1 | `GITHUB_TOKEN` | Requires Copilot subscription |
+
+### International Providers
+
+| Provider | Models | API Key | Notes |
+|----------|--------|---------|-------|
+| **DeepSeek** ⭐ | Chat, Coder, Reasoner | `DEEPSEEK_API_KEY` | Powerful reasoning models |
+| **Kimi (Moonshot)** ⭐ | 8K, 32K, 128K | `MOONSHOT_API_KEY` | Long context (128K tokens) |
+
+### Local & Self-Hosted
+
+| Provider | Models | Setup | Notes |
+|----------|--------|-------|-------|
+| **Ollama** | Llama 3, Mistral, CodeLlama | Install Ollama | Run models locally |
+| **LM Studio** | Any GGUF model | Install LM Studio | GUI for local models |
+| **Custom** ⭐ | Your choice | Configure endpoint | vLLM, TGI, llama.cpp, etc. |
+
+⭐ = New providers
+
+## Tools
+
+DevOrch has access to these tools:
+
+| Tool | Description |
+|------|-------------|
+| **shell** | Execute shell commands (quick commands with output capture) |
+| **open_terminal** ⭐ | Open new terminal window for interactive/long-running commands |
+| **terminal_session** ⭐ | Managed background sessions (start, read, send input, stop) |
+| **filesystem** | Read, write, and list files |
+| **search** | Find files by name patterns (glob) |
+| **grep** | Search for text patterns in files |
+| **edit** | Make targeted edits to existing files |
+| **task** | Track progress on multi-step work with visual task list |
+| **websearch** | Search the web for current information (uses DuckDuckGo) |
+| **webfetch** | Fetch and read content from a URL |
+
+### Terminal Session Management
+
+Run long-running servers and interact with them without blocking the chat:
+
+```bash
+# LLM can start a dev server in background
+> terminal_session start vite_server "npm run dev"
+✓ Session 'vite_server' started (PID 12345)
+
+# Continue chatting while server runs
+
+# Check server output
+> terminal_session read vite_server
+[Session 'vite_server' — running]
+VITE v5.0.0 ready in 450 ms
+➜ Local: http://localhost:5173/
+
+# Send input to the process
+> terminal_session send vite_server "rs\n"  # Restart
+
+# Stop when done
+> terminal_session stop vite_server
+```
+
+## Task Tracking
+
+DevOrch can track progress on complex tasks:
+
+```
+╭─────────── Tasks (2/4) ───────────╮
+│   ✓ Create project structure      │
+│   ✓ Set up dependencies           │
+│   ● Installing packages           │
+│   ○ Run initial build             │
+╰───────────────────────────────────╯
+```
+
+Use `/tasks` to view current task list anytime.
+
+## Config Files
+
+DevOrch stores configuration in `~/.devorch/`:
+
+```
+~/.devorch/
+├── config.yaml       # Provider settings and default models
+├── permissions.yaml  # Tool permission rules
+└── sessions.db       # SQLite database for chat history
+```
+
+## Requirements
+
+- Python 3.10+
+- Dependencies:
+  - typer, rich, pydantic
+  - openai, anthropic, google-genai
+  - httpx, keyring, prompt_toolkit
+  - questionary, pyyaml, duckduckgo-search
+
+## License
+
+MIT

devorch-0.1.2.dist-info/RECORD

@@ -0,0 +1,50 @@
+cli/main.py,sha256=ZPLieeimX_dhUNTpvfKJpbeF6I96QBrTuRBKLjCY5yA,59752
+cli/commands/ask.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cli/commands/edit.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cli/commands/run.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+config/permissions.py,sha256=kB0yKLJQ3J5JJlY02MWV5gcs7_lBA1rvfmzfcSPlPCM,8546
+config/profiles.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+config/settings.py,sha256=w5mkKjWG_y3wkI69oEdcz7pl4_xjZMOmpyuwL0Lfqs0,6526
+core/agent.py,sha256=XolPmaEeJhoFbj2UkMGwdB0leFx04mLPqIACT7D2JVU,17484
+core/context.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+core/executor.py,sha256=IbDz9Neb1uZcDx0bn7KTVRsJ_dKXx38BYuTVbkmxPZ0,7952
+core/modes.py,sha256=LUe4wTSrtlETKQMMJMrUCi-URI7JHJR7P2FCsc_ExDQ,4710
+core/planner.py,sha256=fpwU12d6dwCaQoXd2iB6arnuFBJkFYNqRdYJ08onV8I,324
+core/sessions.py,sha256=R33JUlpTFUIRpRZdR9wGYaLM2XRQDj3ndYha4AOl9eU,8829
+core/tasks.py,sha256=MG15rDwQpWNxdplMJSRdtTuMMha6zTCsk5eqdCrMunM,4484
+providers/__init__.py,sha256=LAzZrt77LRhfPiK_BI7nkRibL90gDBsbYqcU3wXPm3w,4119
+providers/anthropic.py,sha256=H7tMzTEEX9CADlOT9bmH0xzoyFErDrwPh3MYBQnBFu0,4764
+providers/base.py,sha256=EJnFNymL4R8bA4jEhuZ4Gk1-ilpzfAm0vK5wSZ2oxEA,1194
+providers/custom.py,sha256=xrAWriF64btcVLAHtHkSUQIFM6nQd1EvJXChWUrC3Yo,6411
+providers/deepseek.py,sha256=jXrxpXlNgPB_R0FaXcmUvio4buY877ZyhF-k4af_-Qg,5628
+providers/gemini.py,sha256=dSI0q5Oh__F99_HbX_qstu5d9tfjba2Vwvc5fXMsfuw,7605
+providers/github_copilot.py,sha256=m2f912QkQnagNvejaqwHIM4ZpIL9n_1Rfv4vWKFqfLc,6505
+providers/groq.py,sha256=HAe2tb-qJsjZmv6kOeBO4ArubbliYVZMJtRyJYNxnjI,4951
+providers/kimi.py,sha256=dtggnoHiaV_RiCjH4OgSsLVK_eQc--NuVtc69IW5AAs,6020
+providers/lmstudio.py,sha256=kcaDCSAZCA_9P2HOhv4Ih7Th4rL93zQtU0a9gQuJuqE,4720
+providers/local.py,sha256=U8fLAHwjwKkPhFBHuV_jUyOi4xI20QKa3FgCR2V8-EQ,7382
+providers/mistral.py,sha256=qc_0r4lZr-xTE4858tra0HlrvAy6Z6ilFmTgE0tJCbs,4942
+providers/openai.py,sha256=XGIVwcPjgEFzCsWrDySr3Y4up4oRbrJbRkulfIXIYRI,3979
+providers/openrouter.py,sha256=b5P6YtfWHJlujZRwjLwqT48yoRzSLe7IbMIVEmf-xi4,6689
+providers/together.py,sha256=KXFjdFRarTOlxptevQw7sp8vKtKB92KTqE-MXZIHd3w,5264
+schemas/message.py,sha256=8UuO5I4UuUqiTlrFNPQCxzw89jHDdMOgjm3lwEsfLBs,588
+schemas/task.py,sha256=Wk8ekd1aTKHzof6o4g_AZQFVVff0ZxU5PeB9cMsBb44,3522
+schemas/tool.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tools/__init__.py,sha256=wB7JfVUA3JHOjXo-EZ9cy8bUpPNnfDDaVgU21kwXmLo,926
+tools/base.py,sha256=8YuUX1nT03QKhXh8E6sf3rfYlX2DVDurypIo38bAvY4,995
+tools/edit.py,sha256=R5B51X9kRU3iR1tIKNMfCwdnWbGmM7Wt18fwLObGTwc,9495
+tools/filesystem.py,sha256=2xPats31mG3j7futGJwdTKp_obziCb1W75-iYfYpVAw,7983
+tools/git.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tools/grep.py,sha256=I-_1jkAqbuBCb3_MP5_kzeew392cB5k2PaNWNCYSvmI,8430
+tools/search.py,sha256=jnH1C_UO47qtWJFyItR5OHf8emESa_nfZgt2eW280Wo,5063
+tools/shell.py,sha256=aOvKl1nZsA3OkCMOgkOKPO7uK_5uzehnRZ1hvh6exKc,1736
+tools/task.py,sha256=4QpfYGpZ3ormH47Fd_5tndINuCxW5WSGHyfc7OAX0p4,2972
+tools/terminal.py,sha256=Jw8VvRZSS3rK78fW1pCfiB87xo9Y9YukwMCCf8KFPao,4846
+tools/terminal_session.py,sha256=H4wyEyXmdwEbkHisNC2lB_gJtFbHHeSTHCDLSfRemLs,11245
+tools/tests.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tools/websearch.py,sha256=Pln5c87av3wADzk4YAEaCh5fHMHWFRt6ZdFQ8e_UW3g,5293
+utils/logger.py,sha256=Nawi9zwKgcotPFbGsvtx5XzWLPEk1OjzAo_h1wx6kuQ,1540
+devorch-0.1.2.dist-info/METADATA,sha256=FJFbBsLJK8iXY4GRByA4xKtRXZpz6I93SSXngkzQDXI,15399
+devorch-0.1.2.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+devorch-0.1.2.dist-info/entry_points.txt,sha256=Au5QOywu9C7Az-rKrl0s2H4SbB2i-_2s5WcgCKMZQgw,42
+devorch-0.1.2.dist-info/RECORD,,

devorch-0.1.2.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.29.0
+Root-Is-Purelib: true
+Tag: py3-none-any

devorch-0.1.2.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+devorch = cli.main:main