Deployment packages the validated source, creates an immutable deployment record, uploads the source, and lets Salambo prepare and activate the managed runtime.

​
1. Validate immediately before deployment

salambo doctor
salambo manifest --path . --json

​
2. Deploy

salambo deploy
Record the deployment identifier, manifest SHA-256, and source SHA-256 printed by the CLI. Runtime preparation is asynchronous; a source upload is not yet proof that an agent can execute.

​
3. Run the hosted smoke test

salambo smoke "Read the workspace README and summarize it in three bullets."
smoke calls the real Responses API using the agent slug from salambo.yaml. It succeeds only when the response reaches completed. For a custom tool, make the expected behavior explicit: 
salambo smoke "Use format_case_reference for case 42 and return only the result."

​
4. Inspect evidence

Open the resulting run in Salambo:
ViewVerify
DetailsDeployment, region, machine, workspace, response count, and final outcome
ActivityAdmission, sandbox, worker, provider, checkpoint, and cleanup sequence
DiagnosticsSanitized technical events and extension hook/tool failures
ResponsesModel output and turn status
ArtifactsFiles intentionally published by the agent

​
5. Test a durable follow-up when state matters

Continue the same response/run through the Responses API when your agent depends on workspace or session state. Confirm the next turn sees the saved workspace and restored model/tool selection.

​
Failure rule

Do not redeploy blindly. Use the failure stage:
  • manifest error: fix source declarations;
  • deployment error: inspect build and activation evidence;
  • run_not_executable: inspect admission and deployment readiness;
  • provider error: inspect credentials, egress, model, and billing;
  • extension timeout/error: inspect the specific tool or hook event;
  • checkpoint error: inspect workspace and cleanup events.
Use run diagnostics for the complete evidence model.