{
  "skill_name": "wf-python",
  "evals": [
    {
      "id": 1,
      "prompt": "Write Python code using the new wf_client API to connect to http://localhost:8765/rpc, discover wf.std.constant, build a typed workflow with Pydantic input/state/output models, then halfway through authoring replace the state/output contract with revised Pydantic models, validate, save artifact version 1, and run it. Explain what WorkflowBuilder infers and what must stay explicit.",
      "expected_output": "A public Python lifecycle using Pydantic contracts and set_contract(), with explicit topology/output and correct validation/save/run behavior.",
      "files": [],
      "assertions": [
        "Uses Pydantic models for workflow contracts instead of hand-written JSON Schema",
        "Uses graph.set_contract() for mid-authoring replacement",
        "Keeps entry point, routes, terminal, and final workflow output explicit",
        "Uses only public wf_client and wf_authoring APIs"
      ]
    },
    {
      "id": 2,
      "prompt": "I have immutable workflow artifact report.v3 on the remote service. Show me Python code using wf_client to load it, edit it with the normal graph builder methods, add a discovered app.default.summarize capability, validate locally and remotely, save version 4, deploy it with a source binding, and start a durable run. Preserve everything I did not edit.",
      "expected_output": "A lossless artifact.edit()/edit_workflow flow that inspects rather than guesses graph identifiers and keeps artifact, deployment, and run separate.",
      "files": [],
      "assertions": [
        "Loads exact artifact version 3 and edits the seeded builder rather than rebuilding",
        "Warns that step IDs and state paths must be inspected rather than guessed",
        "Validates locally and remotely before saving version 4",
        "Creates and validates a deployment before starting a durable run"
      ]
    },
    {
      "id": 3,
      "prompt": "Using only the public Python workflow client, show how to diagnose why artifact invoice.v2 cannot run, select or create a deployment with bindings, validate it, start a run, handle an interrupt, refresh it, and read only 25 trace frames. Include public error handling. Do not use draft workspaces or raw JSON-RPC.",
      "expected_output": "Public object-based diagnosis with DeploymentRequired, explicit bindings, validation, immutable refresh/resume, and a bounded TracePage.",
      "files": [],
      "assertions": [
        "Uses no draft workspace, raw JSON-RPC, codec, or store API",
        "Handles DeploymentRequired without guessing bindings",
        "Uses run.resume(), run.refresh(), and run.trace(start=0, limit=25)",
        "Uses trace.frames and public WorkflowClientError subclasses accurately"
      ]
    }
  ]
}