M2.8: switch over to the new loop

nisse-dev now runs only the conversational loop. The gated state machine
it was built alongside is gone:

- Removed control.py, planner.py, executor.py, approvals.py, gates.py
  (command_form moves to loop/reader.py), publish.py and poller.py, the
  old assembly in agent.py (its shared helpers move to loop/build.py),
  the store's state-machine view (get_state, transition), their tests,
  the old end-to-end and live planning/milestone/gate tests, and
  specs/orchestrator.qnt with its scenarios.
- Roles are driver, helper, expert and classifier; driver is required.
  loop:, roles.planner, roles.executor and tuning.executor are refused
  with what to use instead; tuning.driver takes the turn cap and failure
  limit.
- The benchmark and the capability matrix measure the driver: the
  loop's own system prompt and tools, the task's plan as the agreed
  restatement. Task plans end with finish_milestone, so earlier runs
  show as (old); stored runs' executor tuning reads as the driver's.
- A delegation on the loop records what its helper's alias resolved to
  (L9), as the old path's did.
- The dump shows a work item's revision and what it waits for.
- Behaviour the old tests covered and the loop shares stays covered:
  driver runs that fail on a model call, stop mid-turn, reset the
  failure count; go-aheads ignoring case and punctuation; a request too
  big to fit is never sent; the assembly tests, now on build_loop_agent.

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

nisse-dev/tests/test_llm.py

@@ -183,28 +183,31 @@ def test_malformed_response_raises_llm_error() -> None:
 
 
 ROLES = RoleMap(
-    executor="local/qwen",
-    planner="anthropic/claude-opus-5",
-    helper="anthropic/claude-opus-5",
+    driver="local/qwen",
+    helper="anthropic/claude-sonnet-5",
     expert="anthropic/claude-opus-5",
 )
 
 
 def test_role_map_resolves_and_pins() -> None:
     roles = ROLES
-    assert roles.resolve("executor") == "local/qwen"
+    assert roles.resolve("driver") == "local/qwen"
     assert roles.pinned() == {
-        "executor": "local/qwen",
-        "planner": "anthropic/claude-opus-5",
-        "helper": "anthropic/claude-opus-5",
+        "driver": "local/qwen",
+        "helper": "anthropic/claude-sonnet-5",
         "expert": "anthropic/claude-opus-5",
-        # Unset, the new loop's roles fall back: driver to the planner's
-        # model, classifier to the expert's (L9).
-        "driver": "anthropic/claude-opus-5",
+        # Unset, the classifier falls back to the expert's model (L9).
         "classifier": "anthropic/claude-opus-5",
     }
 
 
+def test_a_pinned_map_from_before_the_driver_reads_its_own_roles() -> None:
+    # Pinned before M2.8: the old loop's roles are there, and are ignored.
+    old = {"planner": "p", "executor": "e", "driver": "d", "helper": "h"}
+    roles = RoleMap.from_pinned(old, ROLES)
+    assert (roles.driver, roles.helper, roles.expert) == ("d", "h", ROLES.expert)
+
+
 def test_unknown_role_raises() -> None:
     with pytest.raises(LLMError, match="unknown role"):
         ROLES.resolve("boss")