Add persistent task workspace alpha

Start the first workspace milestone toward the task-oriented product without changing the existing one-shot vm_run/pyro run contract.

Add a disk-backed task registry in the manager, auto-started task workspaces rooted at /workspace, repeated non-cleaning exec, and persisted command journals exposed through task create/exec/status/logs/delete across the CLI, Python SDK, and MCP server.

Update the public contract, docs, examples, and version/catalog metadata for 2.1.0, and cover the new surface with manager, CLI, SDK, and MCP tests. Validation: UV_CACHE_DIR=.uv-cache make check and UV_CACHE_DIR=.uv-cache make dist-check.

docs/integrations.md

@@ -7,7 +7,7 @@ CLI path in [install.md](install.md) or [first-run.md](first-run.md).
 
 ## Recommended Default
 
-Use `vm_run` first.
+Use `vm_run` first for one-shot commands.
 
 That keeps the model-facing contract small:
 
@@ -16,7 +16,8 @@ That keeps the model-facing contract small:
 - one ephemeral VM
 - automatic cleanup
 
-Only move to lifecycle tools when the agent truly needs VM state across multiple calls.
+Move to `task_*` only when the agent truly needs repeated commands in one workspace across
+multiple calls.
 
 ## OpenAI Responses API
 
@@ -29,6 +30,7 @@ Best when:
 Recommended surface:
 
 - `vm_run`
+- `task_create` + `task_exec` when the agent needs persistent workspace state
 
 Canonical example:
 
@@ -63,17 +65,20 @@ Best when:
 Recommended default:
 
 - `Pyro.run_in_vm(...)`
+- `Pyro.create_task(...)` + `Pyro.exec_task(...)` when repeated workspace commands are required
 
 Lifecycle note:
 
 - `Pyro.exec_vm(...)` runs one command and auto-cleans the VM afterward
 - use `create_vm(...)` + `start_vm(...)` only when you need pre-exec inspection or status before
   that final exec
+- use `create_task(...)` when the agent needs repeated commands in one persistent `/workspace`
 
 Examples:
 
 - [examples/python_run.py](../examples/python_run.py)
 - [examples/python_lifecycle.py](../examples/python_lifecycle.py)
+- [examples/python_task.py](../examples/python_task.py)
 
 ## Agent Framework Wrappers
 
@@ -91,8 +96,8 @@ Best when:
 Recommended pattern:
 
 - keep the framework wrapper thin
-- map framework tool input directly onto `vm_run`
-- avoid exposing lifecycle tools unless the framework truly needs them
+- map one-shot framework tool input directly onto `vm_run`
+- expose `task_*` only when the framework truly needs repeated commands in one workspace
 
 Concrete example: