Files
factorio-learning-environment/data/prompts/postprocessing/backfill_objectives/system_prompt.md
kiankyars a62f7f208c Restructure (#274)
* add changes

* refactor: clean up unused Docker scripts and redundant files

Remove unused and redundant files from fle/cluster/docker/:

- main.py: Redundant Python script that duplicates run_local.sh functionality
  with hardcoded ports and basic container management. Not used in workflow.

- install-docker.sh: AWS EC2-specific setup script with hardcoded instance
  (ec2-18-133-239-115) and outdated Amazon Linux commands. Current workflow
  uses docker-compose instead.

- probe.sh: Simple port checking script using lsof. Redundant since
  docker-compose handles health checks and container status monitoring.

- setup_docker_repo.sh: AWS ECR-specific setup with hardcoded AWS account
  (216370203482). Contains mostly commented code and unused ECR repository
  configuration. Not used in current workflow.

- requirements.txt: Redundant Python dependency file. Docker is a system
  dependency, not a Python package. The Python docker SDK is already
  included in pyproject.toml dependencies.

Kept essential files: Dockerfile, build scripts, run scripts, config/,
mods/, and README.md which are actively used in the Docker workflow.

* refactor: move lib/ and tools/ to mods/, clean up fle/env/utils/ (all deleted files were unused), prep for entrypoints/ refactor

* readd

* last undo

* refactor: move evaluator.py to algorithms/mcts, move experiment entrypoints to entrypoints/, update imports accordingly

* version info

* incorrect gitignore

* style: replace all relative imports in fle.agents with absolute imports

* simplify gitignore

* commit

* gitignore

* redo

* update

* No code is importing the fle.agents.data package/module

* exclude data/prompts from ruff lint/format in pre-commit

* yaml

* Files were cleared but not deleted

* finalize Neel's suggestions

* Jul 12, 2025 at 13:29

* Jul 12, 2025 at 15:47

* push

* Jul 12, 2025 at 16:03

* Jul 12, 2025 at 16:03

* Jul 12, 2025 at 16:03

* fix

* fix

* fix

* push

* push

* Jul 12, 2025 at 17:48

* remove publish on merge
2025-07-17 17:12:47 +03:00

1.4 KiB

You are an AI assistant given a implementation of a factorio objective using the python factorio API, the general description of the implementation and the name of the implementation. Your goal is to analyse the implementation, the name and description and output a objective for this implementation. The objective is something that can be give to someone and from that objective they should create this implementation. Some examples of objectives are "Get one burner mining drill", "Create an automated burner mining mine that transports iron to a chest" etc.

Keep the objectives short and concise. At the same time make them detailed, for instance "Create iron plates for one boiler" is a better objective than "Create iron plates", as the latter is too vague and probably does not give enough detail to match the given implementation to this exact objective. You are also given examples of implementations and correct objectives, use them as style examples.

First think step by step regarding what objective is suitable for the implementation. Then bring out the objective by putting the objective between 2 #OBJECTIVE tags for instance #OBJECTIVE Create iron plates for one boiler #OBJECTIVE Only use two #OBJECTIVE tags in your answer and they should exactly be before and after the generated objective. The output is parsed automatically so do not use the #OBJECTIVE tags anywhere else