Truss Push GitHub Action

- uses: basetenlabs/action-truss-push@v0.1.2
  with:
    truss-directory: "./my-model"
    baseten-api-key: ${{ secrets.BASETEN_API_KEY }}

Deploys a Truss model or Chain to Baseten, waits for the deployment to become active, optionally validates it with a predict request, and cleans up the deployment. For workflow examples, see CI/CD. Models are detected when truss-directory points to a directory containing config.yaml. Chains are detected when truss-directory points to a .py file containing a @chains.mark_entrypoint class. Pin to a specific release tag. Don’t use @main because the action API may change between releases.

Inputs

string

required

Path to a model directory containing config.yaml, or a .py file for Chain deployments.

string

required

Baseten API key. Store this as an encrypted secret. Never hardcode it in your workflow file.

string

default:""

Override the model or Chain name. For models, maps to truss push --model-name. For Chains, sets the chain_name. If empty, the action uses model_name from config.yaml for models. For Chains, it uses the configured Chain name, then falls back to the entrypoint class name.

string

default:""

For models, publish to a specific environment. This input implies publish. For Chains in v0.1.2, this input doesn’t promote the deployment. See regional-environment for Chain validation behavior. If empty, the action doesn’t select an environment.

string

default:"false"

Set to true when environment names a regional environment. The action sends validation requests to the regional endpoint. For Chains in v0.1.2, that endpoint calls the deployment already serving the environment, not the new deployment created by the action. Leave this input set to false to validate the new Chain deployment through its deployment-specific endpoint. Requires environment.

string

default:"true"

Models only. Attach git versioning info (SHA, branch, tag) to the deployment.

string

default:""

Models only. JSON string of labels as key-value pairs, for example {"team": "ml", "project": "llm"}. Attach metadata to track deployments in your CI pipeline.

string

default:""

Models only. Name of the deployment. If empty, defaults to PR-{number}_{sha} on pull requests or {sha} on direct pushes.

string

default:""

Models only. Baseten team name. Set this input when the API key can access multiple teams and the action can’t select one interactively.

string

default:"true"

Deactivate the newly created deployment at the end of the run. Useful for PR checks where you deploy, validate with a predict request, and tear down. Set to false when you want the deployment to remain active for manual inspection or when a model workflow deploys to an environment.The activate and deactivate calls this action makes are rate limited to 20 requests/minute per API key. See management API rate limits if you run high-volume CI.

string

default:""

JSON override for the predict request payload. For models, if empty, the action reads model_metadata.example_model_input from config.yaml. For Chains, provide the payload explicitly. The action skips prediction when the resolved JSON value is missing, null, false, 0, an empty string (""), an empty object ({}), or an empty array ([]).

string

default:"45"

Maximum minutes to wait for the deployment to become active. The default (45 minutes) accommodates large model builds like TRT-LLM. Reduce this for smaller models to fail faster.

string

default:"300"

Timeout in seconds for the predict request.

Outputs

string

Baseten deployment ID. Use this to reference the deployment in downstream steps or API calls.

string

Baseten model ID. Set for model deployments only.

string

Baseten Chain ID. Set for Chain deployments only.

string

For Chains, the configured Chain name. For models in v0.1.2, this output is model_name from config.yaml, even when the model-name input overrides the deployed model name.

string

Seconds spent waiting for the deployment to become active after the push call returns. This output doesn’t include time spent inside the push call, so it isn’t the total deployment or build duration.

string

Response body from the predict call, truncated to 4 KB.

string

Final status of the action run. One of: success, deploy_failed, deploy_timeout, predict_failed, cleanup_failed.

Status codes

Status	Description
`success`	Deployment active, prediction passed if the action ran it, and cleanup succeeded if enabled.
`deploy_failed`	The model push or Chain deployment failed. Check the API key. For models, check `config.yaml` and the build output. For Chains, follow the chainlet log URLs in the deploy output.
`deploy_timeout`	Deployment didn’t become active within `deploy-timeout-minutes`. Increase the timeout for large models.
`predict_failed`	Predict request returned an error or timed out. Verify the payload shape matches what the model expects.
`cleanup_failed`	Deployment deactivation failed. The deployment may still be running. Deactivate it manually from the Baseten dashboard.

Deployment naming

For models, the action generates deployment names from Git context unless you override with deployment-name:

Pull requests: PR-{number}_{short_sha} (for example, PR-42_abc1234).
Direct pushes: {short_sha} (for example, abc1234).

Permissions

The action requires only contents: read permission. No additional GitHub token permissions are needed.

permissions:
  contents: read

Reference

Inference API

Management API

CLI reference

SDK reference

Training API

Frontier Gateway API

CI/CD

Truss Push GitHub Action

Inputs

Outputs

Status codes

Deployment naming

Permissions

​Inputs

​Outputs

​Status codes

​Deployment naming

​Permissions

Inputs

Outputs

Status codes

Deployment naming

Permissions