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/src/nisse_dev/loop/agent.py

@@ -37,7 +37,6 @@ from nisse_dev.canonical import (
 from nisse_dev.config import GENERAL
 from nisse_dev.delegation import DELEGATION_INTENT, Delegation
 from nisse_dev.expert import BudgetExhausted, ExpertDesk
-from nisse_dev.gates import command_form
 from nisse_dev.git import GitError
 from nisse_dev.gitea import GiteaClient, GiteaError, Issue
 from nisse_dev.llm import LLMError, RoleMap
@@ -61,7 +60,7 @@ from nisse_dev.loop.items import (
     save,
 )
 from nisse_dev.loop.milestones import OPEN_PR, Milestones
-from nisse_dev.loop.reader import GoAheadReader, is_question
+from nisse_dev.loop.reader import GoAheadReader, command_form, is_question
 from nisse_dev.loop.tools import (
     ASK_HUMAN,
     CLOSE_ITEM,
@@ -75,7 +74,7 @@ from nisse_dev.loop.tools import (
 )
 from nisse_dev.oplog import OpLog
 from nisse_dev.state import StateStore, WorkItem
-from nisse_dev.tools import EXECUTOR_TOOLS, Workspace
+from nisse_dev.tools import EXECUTION_TOOLS, Workspace
 from nisse_dev.transport import InboundMessage, Transport
 from nisse_dev.worker import Worker
 
@@ -113,7 +112,7 @@ _MARKER = re.compile(r"<!-- nisse-item: ([A-Za-z0-9-]+) -->")
 
 # Before the go-ahead the driver may look around (read, list, run a command
 # to reproduce a bug) but not change anything (D1); after it, everything.
-_LOOK = [t for t in EXECUTOR_TOOLS if t["function"]["name"] != "write_file"]
+_LOOK = [t for t in EXECUTION_TOOLS if t["function"]["name"] != "write_file"]
 
 SYSTEM = """You are nisse-dev, a software agent working with the operator on
 the repository {repo}. You are on one work item: issue #{issue}, "{title}".
@@ -1411,12 +1410,7 @@ class LoopAgent:
         default = (
             self._helpers.roles
             if self._helpers
-            else RoleMap(
-                executor="",
-                planner=self._roles.get("planner", ""),
-                helper="",
-                expert="",
-            )
+            else RoleMap(driver=self._roles.get("driver", ""), helper="", expert="")
         )
         pinned = item.data.get("roles") or self._roles
         return RoleMap.from_pinned(dict(pinned), default)
@@ -1454,6 +1448,9 @@ class LoopAgent:
             workspace,
             milestones.git,
             model=helper,
+            backing_model=(
+                self._helpers.backing(helper) if self._helpers.backing else ""
+            ),
             caps=self._helpers.caps,
             cancel=self._cancel,
             reader=self._helpers.reader(roles),
@@ -1737,7 +1734,7 @@ class LoopAgent:
                     *([WAIT_FOR_REVIEW] if loop.pr else []),
                     *([DELEGATE, ASK_EXPERT] if self._helpers else []),
                     *([REPLY] if loop.back_to else []),
-                    *EXECUTOR_TOOLS,
+                    *EXECUTION_TOOLS,
                 ]
             ),
         ]
@@ -1826,7 +1823,7 @@ class LoopAgent:
             text = str(args.get("text", "")).strip()
             rev = loop.rev + 1
             self._store.transcript(item.id, "driver").append(
-                PlanSubmitted(plan=text, model=self._roles.get("planner", ""))
+                PlanSubmitted(plan=text, model=self._roles.get("driver", ""))
             )
             self._fact(item, f"restatement rev-{rev} put up for a go-ahead")
             self._shown[loop.thread] = rev
@@ -1869,7 +1866,7 @@ class LoopAgent:
             summary = str(args.get("summary", "")).strip()
             rev = loop.rev + 1
             self._store.transcript(item.id, "driver").append(
-                PlanSubmitted(plan=summary, model=self._roles.get("planner", ""))
+                PlanSubmitted(plan=summary, model=self._roles.get("driver", ""))
             )
             self._fact(item, f"work proposed as rev-{rev}: {project.repo}, {title}")
             self._shown[loop.thread] = rev
@@ -1899,7 +1896,7 @@ class LoopAgent:
             brief = f"{purpose}\n\nDecisions:\n{decisions}" if decisions else purpose
             rev = loop.rev + 1
             self._store.transcript(item.id, "driver").append(
-                PlanSubmitted(plan=brief, model=self._roles.get("planner", ""))
+                PlanSubmitted(plan=brief, model=self._roles.get("driver", ""))
             )
             self._fact(item, f"new project proposed as rev-{rev}: {name}")
             self._shown[loop.thread] = rev