execution-agent 0.1.0__tar.gz

execution_agent-0.1.0/LICENSE.md

@@ -0,0 +1,46 @@
+MIT License
+
+Copyright (c) 2025 Islem BOUZENIA - SOFTWARELAB
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+THIS SOFTWARE IS BASED ON THE MINI-SWE-AGENT PROJECT, 
+ORIGINAL LICENSE OF MINI-SWE-AGENT BELOW:
+
+MIT License
+
+Copyright (c) 2025 Kilian A. Lieret and Carlos E. Jimenez
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

execution_agent-0.1.0/PKG-INFO

@@ -0,0 +1,231 @@
+Metadata-Version: 2.4
+Name: execution-agent
+Version: 0.1.0
+Summary: Automated project building and test execution inside Docker containers
+Author: Islem Bouzenia
+License: MIT License
+        
+        Copyright (c) 2025 Islem BOUZENIA - SOFTWARELAB
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+        THIS SOFTWARE IS BASED ON THE MINI-SWE-AGENT PROJECT, 
+        ORIGINAL LICENSE OF MINI-SWE-AGENT BELOW:
+        
+        MIT License
+        
+        Copyright (c) 2025 Kilian A. Lieret and Carlos E. Jimenez
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+Project-URL: Repository, https://github.com/sola-st/ExecutionAgent
+Keywords: testing,docker,automation,agents,ci
+Classifier: Development Status :: 4 - Beta
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Software Development :: Testing
+Classifier: Topic :: Software Development :: Build Tools
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: mini-swe-agent
+Requires-Dist: docker
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml
+Requires-Dist: requests
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Dynamic: license-file
+
+# Execution Agent
+
+[![PyPI version](https://img.shields.io/pypi/v/execution-agent)](https://pypi.org/project/execution-agent/)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+An LLM-powered agent that automatically sets up, builds, and runs test suites for software projects inside Docker containers. Given a Git repository, it analyzes the project, creates a Dockerfile, installs dependencies, and executes the test suite — all autonomously.
+
+## Installation
+
+```bash
+pip install execution-agent
+```
+
+Requires Python 3.10+ and Docker installed on the host.
+
+## Quick Start
+
+```bash
+# 1. Set your API key
+export OPENAI_API_KEY="your-api-key"
+
+# 2. Create a project metadata file
+cat > project_meta_data.json << 'EOF'
+{
+  "project_path": "my_project",
+  "project_url": "https://github.com/username/my_project",
+  "language": "Python",
+  "budget": 40
+}
+EOF
+
+# 3. Run the agent
+execution-agent --experiment-file project_meta_data.json
+```
+
+## How It Works
+
+1. **Context gathering** — Clones the repository, inspects CI configs, README, and dependency files
+2. **Dockerfile generation** — Creates a Docker environment tailored to the project
+3. **Build & test** — Iteratively runs commands inside the container to install, build, and test
+4. **Retry with learning** — If the budget is exhausted, retries with lessons from previous attempts
+5. **Forced exit** — As a last resort, a knowledge model synthesizes a final solution from all context
+
+The task is considered successful when ~80%+ of tests pass.
+
+## Command-Line Options
+
+```
+execution-agent --experiment-file META.json [OPTIONS]
+```
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--experiment-file` | Path to project metadata JSON **(required)** | — |
+| `--task` | Custom task string | Auto-generated |
+| `--task-file` | File containing custom task instructions | — |
+| `--model` | LLM model for the agent | `gpt-5-nano` |
+| `--knowledge-model` | LLM model for context analysis | `gpt-5-mini` |
+| `--api-key` | OpenAI API key | `$OPENAI_API_KEY` |
+| `--workspace-root` | Output directory | `execution_agent_workspace` |
+| `--prompt-files` | Custom prompt templates directory | Bundled defaults |
+| `--log-level` | `DEBUG` / `INFO` / `WARNING` / `ERROR` | `INFO` |
+| `--run-log-dir` | Custom directory for run logs | Auto-generated |
+| `--max-retries` | Retries after budget exhaustion | `2` |
+
+You can also run it as a module:
+
+```bash
+python -m execution_agent --experiment-file project_meta_data.json
+```
+
+## Project Metadata Format
+
+```json
+{
+  "project_path": "scipy",
+  "project_name": "SciPy",
+  "project_url": "https://github.com/scipy/scipy",
+  "language": "Python",
+  "budget": 40
+}
+```
+
+| Field | Description |
+|-------|-------------|
+| `project_path` | Directory name for the project |
+| `project_name` | Human-readable name (optional) |
+| `project_url` | Git repository URL |
+| `language` | Primary language: `Python`, `Java`, `Javascript`, `C`, `C++`, `Rust` |
+| `budget` | Maximum execution cycles (steps) |
+
+## Agent Tools
+
+The agent can use these tools during execution:
+
+| Tool | Description |
+|------|-------------|
+| `linux_terminal` | Execute bash commands inside the Docker container |
+| `read_file` | Read file contents |
+| `write_to_file` | Write files (Dockerfiles, scripts, etc.) |
+| `search_docker_image` | Search Docker Hub for base images |
+| `goals_accomplished` | Signal successful task completion |
+
+## Output Structure
+
+```
+execution_agent_workspace/
+├── _run_logs/<project>/<timestamp>/
+│   ├── run.log                    # Human-readable log
+│   ├── run.jsonl                  # Structured JSON log
+│   ├── messages.json              # Full LLM conversation history
+│   ├── replay_trace.sh            # Bash script to replay all commands
+│   ├── tool_metrics.json          # Tool execution statistics
+│   ├── cycles_chats/              # Per-cycle LLM prompts
+│   ├── success_artifacts/         # On success: Dockerfile, commands.sh, launch.sh
+│   └── forced_exit_cycle/         # On budget exhaustion: final attempt artifacts
+└── <project>/                     # Cloned repository
+```
+
+### Reproducing a Successful Run
+
+```bash
+cd execution_agent_workspace/_run_logs/<project>/<timestamp>/success_artifacts/
+./launch.sh
+```
+
+## Retry Mechanism
+
+1. **Attempt 1**: Initial run with full budget
+2. **Attempts 2–N**: Retries informed by lessons from previous attempts
+3. **Forced exit cycle**: If all retries fail, a knowledge model generates a final Dockerfile and test script based on everything learned
+
+Each attempt produces a summary with problems encountered, progress made, and suggestions for the next attempt.
+
+## Language Support
+
+Built-in guidelines are included for:
+Python, Java, JavaScript/TypeScript, C, C++, and Rust.
+
+## Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `OPENAI_API_KEY` | API key for LLM access (required) |
+| `OPENAI_MODEL` | Default model (fallback for `--model`) |
+| `KNOWLEDGE_MODEL` | Default knowledge model (fallback for `--knowledge-model`) |
+
+## License
+
+MIT — see [LICENSE.md](LICENSE.md) for details.
+
+Based on [mini-swe-agent](https://github.com/SWE-agent/mini-SWE-agent) by Kilian Lieret and Carlos E. Jimenez.

execution_agent-0.1.0/README.md

@@ -0,0 +1,153 @@
+# Execution Agent
+
+[![PyPI version](https://img.shields.io/pypi/v/execution-agent)](https://pypi.org/project/execution-agent/)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+An LLM-powered agent that automatically sets up, builds, and runs test suites for software projects inside Docker containers. Given a Git repository, it analyzes the project, creates a Dockerfile, installs dependencies, and executes the test suite — all autonomously.
+
+## Installation
+
+```bash
+pip install execution-agent
+```
+
+Requires Python 3.10+ and Docker installed on the host.
+
+## Quick Start
+
+```bash
+# 1. Set your API key
+export OPENAI_API_KEY="your-api-key"
+
+# 2. Create a project metadata file
+cat > project_meta_data.json << 'EOF'
+{
+  "project_path": "my_project",
+  "project_url": "https://github.com/username/my_project",
+  "language": "Python",
+  "budget": 40
+}
+EOF
+
+# 3. Run the agent
+execution-agent --experiment-file project_meta_data.json
+```
+
+## How It Works
+
+1. **Context gathering** — Clones the repository, inspects CI configs, README, and dependency files
+2. **Dockerfile generation** — Creates a Docker environment tailored to the project
+3. **Build & test** — Iteratively runs commands inside the container to install, build, and test
+4. **Retry with learning** — If the budget is exhausted, retries with lessons from previous attempts
+5. **Forced exit** — As a last resort, a knowledge model synthesizes a final solution from all context
+
+The task is considered successful when ~80%+ of tests pass.
+
+## Command-Line Options
+
+```
+execution-agent --experiment-file META.json [OPTIONS]
+```
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--experiment-file` | Path to project metadata JSON **(required)** | — |
+| `--task` | Custom task string | Auto-generated |
+| `--task-file` | File containing custom task instructions | — |
+| `--model` | LLM model for the agent | `gpt-5-nano` |
+| `--knowledge-model` | LLM model for context analysis | `gpt-5-mini` |
+| `--api-key` | OpenAI API key | `$OPENAI_API_KEY` |
+| `--workspace-root` | Output directory | `execution_agent_workspace` |
+| `--prompt-files` | Custom prompt templates directory | Bundled defaults |
+| `--log-level` | `DEBUG` / `INFO` / `WARNING` / `ERROR` | `INFO` |
+| `--run-log-dir` | Custom directory for run logs | Auto-generated |
+| `--max-retries` | Retries after budget exhaustion | `2` |
+
+You can also run it as a module:
+
+```bash
+python -m execution_agent --experiment-file project_meta_data.json
+```
+
+## Project Metadata Format
+
+```json
+{
+  "project_path": "scipy",
+  "project_name": "SciPy",
+  "project_url": "https://github.com/scipy/scipy",
+  "language": "Python",
+  "budget": 40
+}
+```
+
+| Field | Description |
+|-------|-------------|
+| `project_path` | Directory name for the project |
+| `project_name` | Human-readable name (optional) |
+| `project_url` | Git repository URL |
+| `language` | Primary language: `Python`, `Java`, `Javascript`, `C`, `C++`, `Rust` |
+| `budget` | Maximum execution cycles (steps) |
+
+## Agent Tools
+
+The agent can use these tools during execution:
+
+| Tool | Description |
+|------|-------------|
+| `linux_terminal` | Execute bash commands inside the Docker container |
+| `read_file` | Read file contents |
+| `write_to_file` | Write files (Dockerfiles, scripts, etc.) |
+| `search_docker_image` | Search Docker Hub for base images |
+| `goals_accomplished` | Signal successful task completion |
+
+## Output Structure
+
+```
+execution_agent_workspace/
+├── _run_logs/<project>/<timestamp>/
+│   ├── run.log                    # Human-readable log
+│   ├── run.jsonl                  # Structured JSON log
+│   ├── messages.json              # Full LLM conversation history
+│   ├── replay_trace.sh            # Bash script to replay all commands
+│   ├── tool_metrics.json          # Tool execution statistics
+│   ├── cycles_chats/              # Per-cycle LLM prompts
+│   ├── success_artifacts/         # On success: Dockerfile, commands.sh, launch.sh
+│   └── forced_exit_cycle/         # On budget exhaustion: final attempt artifacts
+└── <project>/                     # Cloned repository
+```
+
+### Reproducing a Successful Run
+
+```bash
+cd execution_agent_workspace/_run_logs/<project>/<timestamp>/success_artifacts/
+./launch.sh
+```
+
+## Retry Mechanism
+
+1. **Attempt 1**: Initial run with full budget
+2. **Attempts 2–N**: Retries informed by lessons from previous attempts
+3. **Forced exit cycle**: If all retries fail, a knowledge model generates a final Dockerfile and test script based on everything learned
+
+Each attempt produces a summary with problems encountered, progress made, and suggestions for the next attempt.
+
+## Language Support
+
+Built-in guidelines are included for:
+Python, Java, JavaScript/TypeScript, C, C++, and Rust.
+
+## Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `OPENAI_API_KEY` | API key for LLM access (required) |
+| `OPENAI_MODEL` | Default model (fallback for `--model`) |
+| `KNOWLEDGE_MODEL` | Default knowledge model (fallback for `--knowledge-model`) |
+
+## License
+
+MIT — see [LICENSE.md](LICENSE.md) for details.
+
+Based on [mini-swe-agent](https://github.com/SWE-agent/mini-SWE-agent) by Kilian Lieret and Carlos E. Jimenez.

execution_agent-0.1.0/pyproject.toml

@@ -0,0 +1,73 @@
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+
+[project]
+name = "execution-agent"
+version = "0.1.0"
+description = "Automated project building and test execution inside Docker containers"
+readme = "README.md"
+requires-python = ">=3.10"
+license = {file = "LICENSE.md"}
+keywords = ["testing", "docker", "automation", "agents", "ci"]
+authors = [
+    {name = "Islem Bouzenia"},
+]
+
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Software Development :: Testing",
+    "Topic :: Software Development :: Build Tools",
+]
+
+dependencies = [
+    "mini-swe-agent",
+    "docker",
+    "pydantic >= 2.0",
+    "pyyaml",
+    "requests",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest",
+    "pytest-cov",
+    "pytest-asyncio",
+    "ruff",
+]
+
+[project.urls]
+Repository = "https://github.com/sola-st/ExecutionAgent"
+
+[project.scripts]
+execution-agent = "execution_agent.main:main"
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["execution_agent*"]
+
+[tool.setuptools.package-data]
+execution_agent = ["prompt_files/*", "commands_interface.json"]
+
+[tool.ruff]
+line-length = 120
+indent-width = 4
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I001", "UP", "B006", "B007"]
+ignore = ["E501", "E402", "E722"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"

execution_agent-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

execution_agent-0.1.0/src/execution_agent/__init__.py

@@ -0,0 +1,8 @@
+"""ExecutionAgent — automated project building and testing in Docker."""
+
+from pathlib import Path
+
+__version__ = "0.1.0"
+
+package_dir = Path(__file__).resolve().parent
+prompt_files_dir = package_dir / "prompt_files"

execution_agent-0.1.0/src/execution_agent/__main__.py

@@ -0,0 +1,5 @@
+"""Allow running as `python -m execution_agent`."""
+
+from execution_agent.main import main
+
+raise SystemExit(main())