Document the agent-workspace vision

Clarify that pyro should evolve into a disposable workspace for agents instead of drifting into a secure CI or task-runner identity.

Add a dedicated vision doc that captures the product thesis, anti-goals, naming guidance, and the future interaction model around workspaces, shells, services, snapshots, and reset. Link that doc from the README landing path and persistent task section so the distinction is visible to new users.

Keep the proposed workspace and shell primitives explicitly illustrative so the vision sharpens direction without silently changing the current public contract.

README.md

@@ -15,6 +15,7 @@ It exposes the same runtime in three public forms:
 ## Start Here
 
 - Install: [docs/install.md](docs/install.md)
+- Vision: [docs/vision.md](docs/vision.md)
 - First run transcript: [docs/first-run.md](docs/first-run.md)
 - Terminal walkthrough GIF: [docs/assets/first-run.gif](docs/assets/first-run.gif)
 - PyPI package: [pypi.org/project/pyro-mcp](https://pypi.org/project/pyro-mcp/)
@@ -198,6 +199,11 @@ The walkthrough GIF above was rendered from [docs/assets/first-run.tape](docs/as
 Use `pyro run` for one-shot commands. Use `pyro task ...` when you need repeated commands in one
 workspace without recreating the sandbox every time.
 
+The project direction is an agent workspace, not a CI job runner. Persistent
+tasks are meant to let an agent stay inside one bounded sandbox across multiple
+steps. See [docs/vision.md](docs/vision.md) for the product thesis and the
+longer-term interaction model.
+
 ```bash
 pyro task create debian:12 --source-path ./repo
 pyro task sync push TASK_ID ./changes --dest src