@elizaos/sweagent-root 2.0.0-alpha

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Shaw Walters and elizaOS Contributors
+
+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.

package/README.md

@@ -0,0 +1,270 @@
+# SWE-agent
+
+> AI-powered Software Engineering Agent with Python, TypeScript, and Rust implementations
+
+[![Version](https://img.shields.io/badge/version-1.1.0-blue.svg)](https://github.com/elizaos/eliza)
+[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
+
+SWE-agent is an autonomous software engineering agent that can solve coding tasks, fix bugs, and implement features across codebases. This package provides production-ready implementations in three languages with full feature parity.
+
+## Features
+
+- **Multi-language Support**: Full implementations in Python, TypeScript, and Rust
+- **Flexible Deployment**: Docker-based isolation or local execution
+- **Multiple LLM Backends**: OpenAI, Anthropic Claude, Google Gemini, and more via LiteLLM
+- **Batch Processing**: Run on multiple problem instances in parallel
+- **Configurable Tools**: Extensible command set for code editing, search, and navigation
+- **History Processing**: Intelligent context management for long interactions
+- **Retry Mechanisms**: Smart retry loops with reviewers and choosers
+
+## Installation
+
+### TypeScript
+
+```bash
+npm install @elizaos/sweagent
+# or
+bun add @elizaos/sweagent
+```
+
+### Python
+
+```bash
+pip install sweagent
+# or using uv
+uv pip install sweagent
+```
+
+### Rust
+
+Add to your `Cargo.toml`:
+
+```toml
+[dependencies]
+elizaos-sweagent = "1.1.0"
+```
+
+## Quick Start
+
+### TypeScript
+
+```typescript
+import { RunSingle, RunSingleConfig } from '@elizaos/sweagent';
+
+const config: RunSingleConfig = {
+  agent: {
+    model: { name: 'claude-3-5-sonnet-20241022' }
+  },
+  env: {
+    repo: { github_url: 'https://github.com/owner/repo' }
+  },
+  problem_statement: {
+    type: 'text',
+    text: 'Fix the bug in main.py',
+    id: 'bug-123'
+  }
+};
+
+const runner = RunSingle.fromConfig(config);
+const result = await runner.run();
+```
+
+### Python
+
+```python
+from sweagent.run.run_single import run
+
+result = run(
+    model_name="claude-3-5-sonnet-20241022",
+    problem_statement="Fix the bug in main.py",
+    repo="https://github.com/owner/repo"
+)
+```
+
+### Rust
+
+```rust
+use elizaos_sweagent::run::{RunSingle, RunSingleConfig};
+
+#[tokio::main]
+async fn main() -> anyhow::Result<()> {
+    let config = RunSingleConfig::default();
+    let mut runner = RunSingle::from_config(config)?;
+    let result = runner.run().await?;
+    Ok(())
+}
+```
+
+### CLI
+
+```bash
+# TypeScript CLI
+npx sweagent run --agent.model.name=gpt-4 --problem_statement.path=issue.md
+
+# Python CLI
+sweagent run --agent.model.name gpt-4 --problem_statement.path issue.md
+
+# Rust CLI
+cargo run --bin sweagent -- run --agent.model.name=gpt-4 --problem_statement.path=issue.md
+```
+
+## Configuration
+
+SWE-agent uses YAML configuration files. A typical configuration looks like:
+
+```yaml
+agent:
+  model:
+    name: claude-3-5-sonnet-20241022
+    per_instance_cost_limit: 3.0
+  templates:
+    system_template: |
+      You are a software engineering expert...
+
+env:
+  deployment:
+    type: docker
+    image: python:3.11
+  repo:
+    type: github
+    github_url: https://github.com/owner/repo
+
+tools:
+  execution_timeout: 500
+  submit_command: submit
+```
+
+See the `config/` directory for example configurations.
+
+## Project Structure
+
+```
+packages/sweagent/
+├── python/           # Python implementation
+│   ├── sweagent/     # Core package
+│   └── tests/        # Python tests
+├── typescript/       # TypeScript implementation
+│   ├── src/          # Source code
+│   └── tests/        # TypeScript tests
+├── rust/             # Rust implementation
+│   ├── src/          # Source code
+│   └── tests/        # Rust tests
+├── config/           # Shared YAML configurations
+├── scripts/          # Build and test scripts
+└── package.json      # Root orchestration
+```
+
+## Development
+
+### Running Tests
+
+All tests can be run from the root:
+
+```bash
+# Run all tests (TypeScript, Python, Rust)
+bun run test
+
+# Individual language tests
+bun run test:ts
+bun run test:python
+bun run test:rust
+```
+
+Or use the test script directly:
+
+```bash
+./scripts/run-all-tests.sh
+```
+
+### Building
+
+```bash
+# Build all implementations
+bun run build
+
+# Individual builds
+bun run build:ts
+bun run build:rust
+bun run build:python
+```
+
+### Linting
+
+```bash
+# Lint all
+bun run lint
+
+# Individual
+bun run lint:check    # TypeScript
+bun run lint:rust
+bun run lint:python
+```
+
+## Architecture
+
+### Agent
+
+The agent module handles the core problem-solving loop:
+
+- **DefaultAgent**: Main agent implementation with configurable models and tools
+- **RetryAgent**: Wrapper that retries with different configurations
+- **Models**: LiteLLM, Human, Replay, InstantEmptySubmit models
+- **History Processors**: Context management for conversation history
+
+### Environment
+
+The environment module provides isolated execution:
+
+- **SWEEnv**: Main environment orchestrator
+- **Deployment**: Docker-based or mock deployments
+- **Repo**: GitHub, local, or pre-existing repository sources
+
+### Tools
+
+The tools module provides command parsing and execution:
+
+- **Bundle**: Tool definitions with arguments and documentation
+- **Parsing**: Multiple parse functions (ThoughtAction, XML, JSON, FunctionCalling)
+- **Registry**: Tool registration and discovery
+
+### Run
+
+The run module handles execution:
+
+- **RunSingle**: Single instance runner
+- **RunBatch**: Batch processing with parallelism
+- **Hooks**: Extension points for monitoring and actions
+
+## API Reference
+
+### TypeScript
+
+See TypeScript type definitions in `typescript/src/index.ts`.
+
+### Python
+
+See Python docstrings and type hints in `python/sweagent/`.
+
+### Rust
+
+Generate docs with:
+
+```bash
+cd rust && cargo doc --open
+```
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes ensuring parity across all three implementations
+4. Add tests for new functionality
+5. Submit a pull request
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.
+
+## Acknowledgments
+
+Based on the original [SWE-agent](https://github.com/princeton-nlp/SWE-agent) by Princeton NLP.

package/package.json

@@ -0,0 +1,71 @@
+{
+  "name": "@elizaos/sweagent-root",
+  "private": false,
+  "version": "2.0.0-alpha",
+  "description": "SWE-agent: AI software engineering agent with Python, TypeScript, and Rust implementations",
+  "type": "module",
+  "main": "typescript/dist/index.js",
+  "types": "typescript/dist/index.d.ts",
+  "exports": {
+    "./package.json": "./package.json",
+    ".": {
+      "types": "./typescript/dist/index.d.ts",
+      "import": "./typescript/dist/index.js",
+      "default": "./typescript/dist/index.js"
+    },
+    "./rust": {
+      "import": "./rust/pkg/node/elizaos_sweagent.js"
+    }
+  },
+  "files": [
+    "typescript/dist",
+    "README.md",
+    "python",
+    "rust/src",
+    "rust/Cargo.toml",
+    "rust/pkg"
+  ],
+  "keywords": [
+    "software-engineering",
+    "agent",
+    "ai",
+    "automation",
+    "development-tools",
+    "swe-agent",
+    "elizaos"
+  ],
+  "author": "elizaOS",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/elizaos/eliza.git"
+  },
+  "scripts": {
+    "build": "bun run build:ts && bun run build:rust && bun run build:python",
+    "build:ts": "cd typescript && bun run build",
+    "build:rust": "test -d rust && cd rust && cargo build --release || echo 'Rust build skipped - no rust directory'",
+    "build:python": "test -d python && cd python && (python3 -m build 2>/dev/null || pyproject-build) || echo 'Python build skipped - no python directory'",
+    "dev": "cd typescript && bun --hot build.ts",
+    "test": "bun run test:ts && bun run test:rust && bun run test:python",
+    "test:ts": "cd typescript && bun run build && vitest run",
+    "test:rust": "test -d rust && cd rust && cargo test || echo 'Rust tests skipped'",
+    "test:python": "test -d python && cd python && pytest -p no:anchorpy --asyncio-mode=auto",
+    "typecheck": "tsc --noEmit -p typescript/tsconfig.json",
+    "lint": "bunx @biomejs/biome check --write ./typescript",
+    "lint:check": "bunx @biomejs/biome check ./typescript",
+    "lint:rust": "test -d rust && cd rust && cargo clippy --all-targets --fix --allow-dirty --allow-staged -- -D warnings && cargo fmt || echo 'Rust lint skipped'",
+    "lint:python": "test -d python && cd python && ruff check --fix . && ruff format . || echo 'Python lint skipped'",
+    "clean": "rm -rf typescript/dist python/dist rust/target .turbo node_modules"
+  },
+  "devDependencies": {
+    "@biomejs/biome": "^2.3.11",
+    "@types/bun": "^1.3.5",
+    "@types/node": "^25.0.3",
+    "typescript": "^5.9.3",
+    "vitest": "^4.0.17"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "gitHead": "53fe0ff5652913ee99f49d363262dc5291993e26"
+}

package/python/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 John Yang, Carlos E. Jimenez, Alexander Wettig, Shunyu Yao, Karthik Narasimhan, Ofir Press
+
+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.

package/python/config/README.md

@@ -0,0 +1,15 @@
+* Default config: `anthropic_filemap.yaml`
+* `swebench_submissions`: Configs that were used for swebench submissions
+* `sweagent_0_7`: Configs from SWE-agent 0.7, similar to the one used in the paper
+* `exotic`: Various specific configurations that might be more of niche interest
+* `human`: Demo/debug configs that have the human type commands and run without a LM
+* `demo`: Configs for demonstrations/talks
+* Configs for running with SWE-smith are at https://github.com/SWE-bench/SWE-smith/blob/main/agent/swesmith_infer.yaml
+
+🔗 Tutorial on [adding custom tools](https://swe-agent.com/latest/usage/adding_custom_tools/)
+🔗 For more information on config files, visit [our documentation website][docs].
+
+You can also find the corresponding markdown files in the [`docs/` folder][source].
+
+[docs]: https://swe-agent.com/latest/config/config
+[source]: https://github.com/SWE-agent/SWE-agent/tree/main/docs

package/python/config/bash_only.yaml

@@ -0,0 +1,222 @@
+# This config is a super basic, stripped down config that should be compatible with any instruction following LM
+agent:
+  type: default
+  templates:
+    system_template: |-
+      You are a helpful assistant that can interact multiple times with a computer shell to solve programming tasks.
+      You operate in a REPL (Read-Eval-Print Loop) environment where you must issue exactly ONE command at a time.
+      Your response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).
+
+      Include a THOUGHT section before your command where you explain your reasoning process.
+      Format your response as:
+
+      THOUGHT: Your reasoning and analysis here
+
+      ```bash
+      your_command_here
+      ```
+
+      Failure to follow these rules will cause your response to be rejected.
+    instance_template: |-
+      <uploaded_files>
+      {{working_dir}}
+      </uploaded_files>
+
+      <pr_description>
+      I've uploaded a python code repository in the directory {{working_dir}}.
+      Consider the following PR description:
+      {{problem_statement}}
+      </pr_description>
+
+      <instructions>
+      # Task Instructions
+
+      ## Overview
+      You're a software engineer interacting continuously with a computer shell in a REPL (Read-Eval-Print Loop) environment.
+      You'll be helping implement necessary changes to meet requirements in the PR description.
+      Your task is specifically to make changes to non-test files in the {{working_dir}} directory in order to fix the issue described in the PR description in a way that is general and consistent with the codebase.
+
+      IMPORTANT: This is an interactive process where you will think and issue ONE command, see its result, then think and issue your next command.
+
+      For each response:
+      1. Include a THOUGHT section explaining your reasoning and what you're trying to accomplish
+      2. Provide exactly ONE bash command to execute
+
+      ## Important Boundaries
+      - MODIFY: Regular source code files in {{working_dir}}
+      - DO NOT MODIFY: Tests, configuration files (pyproject.toml, setup.cfg, etc.)
+
+      ## Recommended Workflow
+      1. Analyze the codebase by finding and reading relevant files
+      2. Create a script to reproduce the issue
+      3. Edit the source code to resolve the issue
+      4. Verify your fix works by running your script again
+      5. Test edge cases to ensure your fix is robust
+
+      ## Command Execution Rules
+      You are operating in a REPL (Read-Eval-Print Loop) environment where:
+      1. You write a single command
+      2. The system executes that command
+      3. You see the result
+      4. You write your next command
+
+      Each response should include:
+      1. A **THOUGHT** section where you explain your reasoning and plan
+      2. A single bash code block with your command
+
+      Format your responses like this:
+      ```
+      THOUGHT: Here I explain my reasoning process, analysis of the current situation,
+      and what I'm trying to accomplish with the command below.
+
+      ```bash
+      your_command_here
+      ```
+      ```
+
+      Commands must be specified in a single bash code block:
+
+      ```bash
+      your_command_here
+      ```
+
+      **CRITICAL REQUIREMENTS:**
+      - Your response SHOULD include a THOUGHT section explaining your reasoning
+      - Your response MUST include EXACTLY ONE bash code block
+      - This bash block MUST contain EXACTLY ONE command (or a set of commands connected with && or ||)
+      - If you include zero or multiple bash blocks, or no command at all, YOUR RESPONSE WILL FAIL
+      - Do NOT try to run multiple independent commands in separate blocks in one response
+
+      Example of a CORRECT response:
+      <example_response>
+      THOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
+
+      ```bash
+      ls -la
+      ```
+      </example_response>
+
+      Example of an INCORRECT response:
+      <example_response>
+      THOUGHT: I need to examine the codebase and then look at a specific file. I'll run multiple commands to do this.
+
+      ```bash
+      ls -la
+      ```
+
+      Now I'll read the file:
+
+      ```bash
+      cat file.txt
+      ```
+      </example_response>
+
+      If you need to run multiple commands, either:
+      1. Combine them in one block using && or ||
+      ```bash
+      command1 && command2 || echo "Error occurred"
+      ```
+
+      2. Wait for the first command to complete, see its output, then issue the next command in your following response.
+
+      ## Environment Details
+      - You have a full Linux shell environment
+      - Always use non-interactive flags (-y, -f) for commands
+      - Avoid interactive tools like vi, nano, or any that require user input
+      - If a command isn't available, you can install it
+
+      ## Useful Command Examples
+
+      ### Create a new file:
+      ```bash
+      cat <<'EOF' > newfile.py
+      import numpy as np
+      hello = "world"
+      print(hello)
+      EOF
+      ```
+
+      ### Edit files with sed:
+      ```bash
+      # Replace all occurrences
+      sed -i 's/old_string/new_string/g' filename.py
+
+      # Replace only first occurrence
+      sed -i 's/old_string/new_string/' filename.py
+
+      # Replace first occurrence on line 1
+      sed -i '1s/old_string/new_string/' filename.py
+
+      # Replace all occurrences in lines 1-10
+      sed -i '1,10s/old_string/new_string/g' filename.py
+      ```
+
+      ### View file content:
+      ```bash
+      # View specific lines with numbers
+      nl -ba filename.py | sed -n '10,20p'
+      ```
+
+      ### Any other command you want to run
+      ```bash
+      anything
+      ```
+
+      ## Submission
+      When you've completed your changes or can't make further progress:
+      ```bash
+      submit
+      ```
+
+      We'll automatically save your work and have maintainers evaluate it.
+      </instructions>
+    next_step_template: |-
+      <observation>
+      {{observation}}
+      </observation>
+    next_step_no_output_template: |-
+      <warning>
+      Your last command ran successfully and did not produce any output.
+      </warning>
+    max_observation_length: 10_000
+    next_step_truncated_observation_template: |-
+      <warning>
+      The output of your last command was too long.
+      Please try a different command that produces less output.
+      If you're looking at a file you can try use head, tail or sed to view a smaller number of lines selectively.
+      If you're using grep or find and it produced too much output, you can use a more selective search pattern.
+      If you really need to see something from the full command's output, you can redirect output to a file and then search in that file.
+      </warning>
+
+      <observation_head>
+      {{observation[ : max_observation_length // 2]}}
+      </observation_head>
+
+      <elided_chars>
+      {{elided_chars}} characters elided
+      </elided_chars>
+
+      <observation_tail>
+      {{observation[- max_observation_length // 2:]}}
+      </observation_tail>
+    command_cancelled_timeout_template: |-
+      <warning>
+      The command '{{command}}' was cancelled because it took more than {{timeout}} seconds to complete.
+      It may have been waiting for user input or otherwise blocked.
+      Please try a different command.
+      </warning>
+  tools:
+    execution_timeout: 60
+    bundles:
+      - path: tools/submit
+    parse_function:
+      type: single_bash_code_block
+  model:
+    per_instance_cost_limit: 3
+    per_instance_call_limit: 250
+    total_cost_limit: 1500.0
+    temperature: 0.0
+    delay: 0.0
+    retry:
+      retries: 6
+      max_wait: 30