Put work items in the state store, and bind the log to them (M1.1)

Development Plan M1.1, as discussed.

- Schema v4: a work_items table (id, scope, title, status, outcome,
  position, data) and an agent row whose active_item points at one
  (NULL: idle). Canonical events and intents carry their work item, and
  events their actor. Older stores are refused with a clear message:
  there was no production data, so no migration (the mechanism stays).
- The log is reached through a Transcript bound to one work item and
  one actor: store.transcript(item, actor) reads only that item and
  writes with both. The planner, executor, delegation and expert desk
  get one per call from the orchestrator instead of holding the store,
  so a component can neither read another task's events (the planner
  read every earlier task's, #78) nor write without attribution.
  store.all_events() is kept for readers that span items (evaluation
  capture, dumps). Intents are begun through the transcript or with
  work_item=, so each belongs to its item.
- The orchestrator opens a work item on 'use', closes it with its
  outcome (completed or abandoned), and carries what the operator said
  while idle into the new item as copies with their origin, so a task
  sent before 'use' is still planned from (D1). control.py keeps its
  state machine through get_state()/transition(), now over the active
  work item, until M2.6 retires it.
- nisse_dev.dump shows work items and each event's item and actor.

Tests: test_work_items.py (scoping, attribution, intent ownership,
restart, outcomes, carried messages, a second task never seeing the
first); the suites updated for the per-call transcript.

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/bench/runner.py

@@ -168,8 +168,16 @@ def run_task(
         )
         task.seed_into(workspace.root)
         store = StateStore(root / "state.db", oplog=OpLog("nisse-bench", io.StringIO()))
-        store.append_event(PlanSubmitted(plan=task.plan, model="benchmark"))
-        store.append_event(UserMessage(text="start milestone 1", source="benchmark"))
+        # One work item per run, as the agent's own tasks are (L1).
+        store.open_work_item(
+            "bench", title=task.name, position="EXECUTING", cause="benchmark run"
+        )
+        store.transcript("bench", "planner").append(
+            PlanSubmitted(plan=task.plan, model="benchmark")
+        )
+        store.transcript("bench", "operator").append(
+            UserMessage(text="start milestone 1", source="benchmark")
+        )
 
         meter = MeteringClient(client, facts)
         trims_before = getattr(client, "trimmed_requests", 0)
@@ -177,7 +185,6 @@ def run_task(
         roles = RoleMap(executor=model, planner=model, helper=model, expert=model)
         executor = LLMExecutor(
             meter,
-            store,
             roles,
             workspace,
             max_turns=tuning.executor.max_turns,
@@ -185,14 +192,14 @@ def run_task(
         )
         started = time.monotonic()
         try:
-            outcome = executor.run(1)
+            outcome = executor.run(store.transcript("bench", "executor"), 1)
             status, detail = outcome.status, outcome.note
         except Exception as exc:  # noqa: BLE001 -- recorded, the benchmark goes on
             status, detail = "error", repr(exc)
         wall = time.monotonic() - started
 
         success, check_output = task.run_check(workspace.root)
-        failed, invented = _count(store.read_events())
+        failed, invented = _count(store.transcript("bench", "executor").read())
         store.close()
 
     return RunRecord(