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_context.py

@@ -9,8 +9,6 @@ import pytest
 from nisse_dev.canonical import (
     AssistantText,
     CanonicalEvent,
-    GateOpened,
-    PlanSubmitted,
     StoredEvent,
     ToolCall,
     ToolResult,
@@ -25,8 +23,7 @@ from nisse_dev.context import (
     fit,
     head_and_tail,
 )
-from nisse_dev.executor import LLMExecutor
-from nisse_dev.llm import RoleMap
+from nisse_dev.loop.driver import Driver
 from nisse_dev.oplog import OpLog
 from nisse_dev.state import StateStore
 
@@ -230,70 +227,27 @@ def test_the_catalog_reads_each_models_limits() -> None:
 
 
 def test_a_role_on_a_model_without_a_window_is_refused() -> None:
-    CATALOG.require_limits({"executor": "llama3.2", "planner": "claude-haiku-4-5"})
-    with pytest.raises(UnknownLimits, match="executor='undeclared'"):
-        CATALOG.require_limits({"executor": "undeclared", "planner": "llama3.2"})
+    CATALOG.require_limits({"driver": "llama3.2", "helper": "claude-haiku-4-5"})
+    with pytest.raises(UnknownLimits, match="driver='undeclared'"):
+        CATALOG.require_limits({"driver": "undeclared", "helper": "llama3.2"})
 
 
-# --- the executor sees the approved plan and what came after ---------------
-
-
-def test_the_executor_sees_only_its_milestone(tmp_path: Path) -> None:
+def test_a_request_that_cannot_fit_ends_the_run(tmp_path: Path) -> None:
+    # Never sent: the driver's run fails and the item waits on the operator,
+    # like any failed call, rather than a server getting a prompt it would
+    # silently cut.
     store = StateStore(tmp_path / "state.db", oplog=OpLog("t", io.StringIO()))
-    for event in (
-        UserMessage(text="use greet: a long planning conversation", source="t"),
-        PlanSubmitted(plan="arch plan", model="m"),
-        UserMessage(text="approve", source="t"),
-        PlanSubmitted(plan="milestone 1: write greet.py", model="m"),
-        GateOpened(gate="milestone-1", reason="plan submitted"),
-        UserMessage(text="start milestone 1", source="t"),
-    ):
-        store.transcript("t", "executor").append(event)
-
-    class Workspace:
-        def describe(self) -> str:
-            return "workspace"
-
-    seen: dict[str, Any] = {}
-
-    class Client:
-        def complete(self, events, tools, model, system=None):
-            seen["events"] = [e.event for e in events]
-            seen["system"] = system
-            return [AssistantText(text="done", model=model)]
-
-    roles = RoleMap(executor="m", planner="m", helper="m", expert="m")
-    LLMExecutor(Client(), roles, Workspace()).run(store.transcript("t", "executor"), 1)
-
-    texts = [getattr(e, "text", None) for e in seen["events"]]
-    assert "start milestone 1" in texts
-    assert "use greet: a long planning conversation" not in texts
-    assert not any(isinstance(e, PlanSubmitted) for e in seen["events"])
-    # The plan rides in the system prompt, which the budget never drops.
-    assert "The approved plan:\nmilestone 1: write greet.py" in seen["system"]
-    assert "arch plan" not in seen["system"]
-
-
-def test_a_request_that_cannot_fit_stops_the_milestone(tmp_path: Path) -> None:
-    # Never sent: the executor stops and asks the operator, like any failed
-    # call, rather than handing a server a prompt it would silently cut.
-    store = StateStore(tmp_path / "state.db", oplog=OpLog("t", io.StringIO()))
-    store.transcript("t", "operator").append(
-        UserMessage(text="start milestone 1", source="t")
-    )
-
-    class Workspace:
-        def describe(self) -> str:
-            return "workspace " + "w" * 20_000  # a system prompt too big to fit
-
+    store.transcript("t", "operator").append(UserMessage(text="go", source="t"))
     inner = RecordingClient()
     client = BudgetedClient(inner, lambda m: (4096, 1024))
-    roles = RoleMap(executor="m", planner="m", helper="m", expert="m")
-    outcome = LLMExecutor(client, roles, Workspace()).run(
-        store.transcript("t", "executor"), 1
+    outcome = Driver(client, "m").run(
+        store.transcript("t", "driver"),
+        system="s" * 20_000,  # a system prompt too big to fit
+        tools=[],
+        workspace=None,
     )
 
-    assert outcome.status == "escalate"
+    assert outcome.kind == "failed"
     assert "fit" in outcome.note
     assert inner.calls == []