Skip to main content

Launch Your First Generation

Start after installation and configuration. Use four terminals so service logs remain visible. The commands assume the venv setup; with Conda, use conda activate magma instead of source .venv/bin/activate.

Terminal 1 — planner

cd ~/magma-workspace/magma-planner-mplib
bash scripts/launch_planner.bash -p 8000

Wait for Uvicorn to report startup. The script builds and starts the container; keep it running. If you chose the native planner installation, use its launch command instead. Start only one planner on port 8000.

Terminal 2 — agent

cd ~/magma-workspace
source .venv/bin/activate
full-history-agent --config ./agent.json

Wait for model loading to finish. In another terminal, check readiness:

curl --fail http://localhost:8888/health

Expect {"status":"ready"}. The configured checkpoint and GPU memory determine how long startup takes.

info

You can run the agent server on another machine or in a container if your local GPU has insufficient memory. Set magma_agent_address to a URL reachable from GEN. Install the agent package in the export environment as well, so its local exporter is available.

Terminal 3 — viewer

cd ~/magma-workspace
source .venv/bin/activate
magma-gen viewer --output-dir ./output

Open http://127.0.0.1:8900. Start the viewer before generation for live updates. The viewer and generator must use the same output directory.

Terminal 4 — generation

cd ~/magma-workspace
source .venv/bin/activate
magma-gen run first_run --preset press_button.ButtonPressPreset1 \
--config-path ./config.yaml --nb-env 1 --nb-branch 1 \
--no-coaching --no-judge --no-randomized

Use a new run name each time: an existing target directory can be cleared by the launcher. Data is saved under ~/magma-workspace/output/first_run. Select the run in the viewer to inspect decisions and tool results. The --gui option, if used, opens the simulation window; it is separate from the graph viewer.

This first run checks the service connections and simulation. It has no semantic answer judge or coaching backend, and a completed run does not guarantee a successful task. For data collection with these features, follow backend configuration.

Export the saved run

After generation finishes, from the workspace with the same environment active:

magma-gen export output/first_run --agent full-history-agent

The local exporter selects eligible examples from the saved graph. A failed or short run may contain no eligible examples. It does not require the agent server to remain running. See export for output files and selection rules.

Stop and troubleshoot

Stop the agent and viewer with Ctrl+C in their terminals. Stop the planner with docker stop magma_mplib from another terminal.

ProblemCheck
Agent connection refusedModel loading completed; /health succeeds; port matches config
Planner connection refusedDocker container is running on port 8000
MPLib dependency conflictPlanner was installed in the generation environment; use Docker or a separate environment
CUDA/Vulkan or model memory errorDrivers, checkpoint size, and GPU memory remaining for simulation
Exporter not foundfull-history-agent was installed in the same environment as MAGMA-GEN
Viewer is emptySame workspace/output path; viewer started before the run; refresh after completion

Next: Inspect the run in the viewer, then read the exported data.