M4.2: the toolchain step

The preflight becomes the toolchain step (D3, as #135 describes it): a
bounded run of the item's driver model, in a transcript of its own,
that makes the build VM and the project's files agree.

- Started by the harness when the VM isn't set up for the project
  (M4.1's checks): it sets the VM up from the repository and edits
  nothing there (no write_file; anything a command changed is reported,
  left for the work).
- Requested by the driver with toolchain_step(reason) once work is
  agreed: it installs, then brings pins, setup docs and CI
  configuration in step; its edits land in the current milestone. The
  driver gets the step's report as the tool's result, not its turns.
- D1 made structural: until the go-ahead the fast path refuses what it
  knows changes something (and anything dangerous), with a pointer to
  the restatement; unknown commands still go to the classifier, so a
  bug can be reproduced before it's restated.
- A `toolchain` actor and view; the walk asks for steps now and then.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

nisse-dev/tests/test_loop_properties.py

@@ -145,6 +145,12 @@ class PolicyModel:
             return [call("ask_human", question=f"talk first {self.n}?")]  # discuss
         if "finish_milestone" not in offered:
             return [call("restate", text=f"restatement {self.n}", changed=f"c{self.n}")]
+        if "toolchain_step" in offered and self.rng.random() < 0.06:
+            # M4.2: the work asks for a toolchain change.
+            return [
+                call("start_milestone", name=f"m{self.n}"),
+                call("toolchain_step", reason=f"needs a tool {self.n}"),
+            ]
         if "delegate" in offered and self.rng.random() < 0.1:
             return [call("delegate", task=f"help {self.n}")]
         allowed = [t for t in facts[-3:] if "allowed this once" in t]