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

tests/integration/test_expert_live.py

@@ -26,7 +26,7 @@ def desk(tmp_path: Path, litellm: LiteLLMClient, live_model: str):
         store = StateStore(
             tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO())
         )
-        return ExpertDesk(litellm, store, roles, budget=budget), store
+        return ExpertDesk(litellm, roles, budget=budget), store
 
     return make
 
@@ -35,8 +35,9 @@ def test_live_consult_parses_against_the_local_schema(desk) -> None:
     expert, store = desk()
 
     answer = expert.ask(
+        store.transcript("t", "expert"),
         "For a single-process agent storing a few thousand rows of task state, "
-        "is SQLite sufficient, or is PostgreSQL warranted? Answer briefly."
+        "is SQLite sufficient, or is PostgreSQL warranted? Answer briefly.",
     )
 
     assert answer.confidence in {"high", "medium", "low"}
@@ -48,7 +49,10 @@ def test_live_consult_parses_against_the_local_schema(desk) -> None:
 
 
 def test_live_budget_stops_a_circling_caller(desk) -> None:
-    expert, _ = desk(budget=1)
-    expert.ask("Name one advantage of WAL mode in SQLite. Be brief.")
+    expert, store = desk(budget=1)
+    expert.ask(
+        store.transcript("t", "expert"),
+        "Name one advantage of WAL mode in SQLite. Be brief.",
+    )
     with pytest.raises(BudgetExhausted):
-        expert.ask("And another?")
+        expert.ask(store.transcript("t", "expert"), "And another?")