Getting Started

SWE-gen wraps the pinned repos/swegen checkout in the SWE-Lego-Live block layout. The pinned repository is recorded as a gitlink under subblock/swegen/repos/swegen and should match commit e804af9.

Prerequisites

Docker - task validation and task execution use containerized Harbor tasks.
Python - install the SWE-gen package from repos/swegen.
GitHub tokens - used for PR collection and PR metadata lookup.
OpenAI-compatible LLM endpoint - used for PR evaluation and task instruction generation.
Claude-compatible task model - used by the task completion stage.

1. Enter the block

Run commands from the block root:

cd subblock/swegen

Confirm the pinned repo exists:

git rev-parse HEAD:repos/swegen

The expected pin for this docs site is:

e804af92aad81f42928453959e24e3f5dc666c44

2. Install the environment

Create the block virtual environment and install SWE-gen:

python3 -m venv artifacts/envs/swegen-env
source artifacts/envs/swegen-env/bin/activate
pip install -U pip
pip install -e repos/swegen/

If you already maintain a compatible environment, activate it before running the scripts. The important requirement is that swegen resolves to the pinned checkout.

3. Configure credentials

Set runtime inputs in the shell or in a local env file that is not committed:

export GITHUB_TOKENS="ghp_xxx,ghp_yyy"
export OPENAI_API_KEY="..."
export ANTHROPIC_API_KEY="$OPENAI_API_KEY"
export OPENAI_API_BASE_URL="https://your-openai-compatible-endpoint/v1"
export ANTHROPIC_BASE_URL="https://your-anthropic-compatible-endpoint"
export OPENAI_MODEL="openai/MiniMax-M2.7"
export ANTHROPIC_MODEL="claude-sonnet-4-6"

GITHUB_TOKEN may also be derived from the first entry in GITHUB_TOKENS. Do not commit tokens or local env files. Keep the OpenAI-compatible and Anthropic-compatible variables aligned with the same provider setup you intend to use for the run. If your shell already contains old ANTHROPIC_API_KEY or ANTHROPIC_BASE_URL values, overwrite or unset them before launching generation; stale Anthropic-compatible variables can make the Claude SDK stage use the wrong endpoint or key.

For reproducible runs on shared machines, use a clean Claude Code config directory so user-level hooks and plugins do not affect task completion:

export CLAUDE_CONFIG_DIR="$PWD/artifacts/claude-config/swegen-clean"
mkdir -p "$CLAUDE_CONFIG_DIR"

4. Run a dry run

Check the block before starting a large batch:

bash scripts/dryrun.sh

This validates expected directories, config values, and basic runtime dependencies. Fix dry-run failures before launching generation.

5. Run a smoke generation

For a small first pass, use a direct swegen create command with explicit limits and shared output paths:

swegen create \
  --input-ids-file artifacts/collected_prs/python_pr_ids.txt \
  --max-pr 1 \
  --n-concurrent 1 \
  --output artifacts/swe_tasks/py-cc \
  --state-dir scripts/.swegen-py \
  --timeout 2400 \
  --cc-timeout 1800 \
  --no-require-issue \
  --min-source-files 1 \
  --max-source-files 10 \
  --docker-prune-batch 0

The language scripts are intended for production batches and read concurrency from config.yaml; prefixing N_CONCURRENT=1 may not override their configured defaults.

For the full multi-language run:

bash scripts/create_all_bg.sh

Per-language scripts are available for py, js, ts, go, c, cpp, java, and rust.

6. Resume after moving nodes

If you restored a March state package into a new clone, check the batch state before running generation. SWE-gen stores batch state under a filename derived from input_ids_file.resolve(). A new clone path creates a new hash even when the relative input file is the same.

For portable recovery, keep these files together:

artifacts/swe_tasks/<lang>-cc/
artifacts/swe_tasks/<lang>-cc/verifiable_tasks.txt
artifacts/swe_tasks/<lang>-cc/.swegen-create-batch/*.json
the matching PR input files in artifacts/collected_prs/

If the clone path changes, rewrite or regenerate the .swegen-create-batch state filenames so they match the current resolved input file paths before launching scripts/create_{lang}.sh.