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/tests/test_expert.py

@@ -20,7 +20,7 @@ from nisse_dev.expert import (
 )
 from nisse_dev.llm import LLMError, RoleMap
 from nisse_dev.oplog import OpLog
-from nisse_dev.state import StateStore
+from nisse_dev.state import StateStore, Transcript
 
 ROLES = RoleMap(
     executor="llama3.2",
@@ -57,8 +57,25 @@ def store(tmp_path: Path) -> StateStore:
     return StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
 
 
-def desk(client: Any, store: StateStore, **kw: Any) -> ExpertDesk:
-    return ExpertDesk(client, store, ROLES, **kw)
+ITEM = "t"  # the work item the consults happen in
+
+
+def log(store: StateStore, item: str = ITEM) -> Transcript:
+    return store.transcript(item, "expert")
+
+
+class Bound:
+    """The desk as the executor uses it: within one work item."""
+
+    def __init__(self, desk: ExpertDesk, store: StateStore, item: str) -> None:
+        self.desk, self.store, self.item = desk, store, item
+
+    def ask(self, question: str, **kw: Any) -> Any:
+        return self.desk.ask(log(self.store, self.item), question, **kw)
+
+
+def desk(client: Any, store: StateStore, item: str = ITEM, **kw: Any) -> Bound:
+    return Bound(ExpertDesk(client, ROLES, **kw), store, item)
 
 
 # --- parsing (the contract is prompt-level, so parsing is the guard) ------
@@ -104,7 +121,7 @@ def test_ask_returns_a_validated_answer(store: StateStore) -> None:
 def test_consult_is_stateless_and_uses_the_consultant_role(
     store: StateStore,
 ) -> None:
-    store.append_event(AssistantText(text="secret repo context", model="m"))
+    log(store).append(AssistantText(text="secret repo context", model="m"))
     client = ScriptedClient([GOOD])
     desk(client, store).ask("Is this API deprecated?")
 
@@ -134,7 +151,7 @@ def test_consults_are_recorded_as_composite_events(store: StateStore) -> None:
     # L9 wants a consult/delegation eval set; reusing the pair gets consult
     # evaluation for free.
     desk(ScriptedClient([GOOD]), store).ask("q")
-    events = [e.event for e in store.read_events()]
+    events = [e.event for e in log(store).read()]
     started = next(e for e in events if isinstance(e, DelegationStarted))
     completed = next(e for e in events if isinstance(e, DelegationCompleted))
     assert started.role == "expert"
@@ -146,7 +163,7 @@ def test_a_failed_consult_is_recorded_too(store: StateStore) -> None:
     with pytest.raises(LLMError):
         desk(ScriptedClient(["waffle", "waffle"]), store).ask("q")
     completed = [
-        e.event for e in store.read_events() if isinstance(e.event, DelegationCompleted)
+        e.event for e in log(store).read() if isinstance(e.event, DelegationCompleted)
     ]
     assert completed[0].exit_status == "failed"
 
@@ -177,10 +194,18 @@ def test_budget_survives_a_restart(tmp_path: Path) -> None:
 def test_budget_counts_only_after_the_task_marker(store: StateStore) -> None:
     d = desk(ScriptedClient([GOOD] * 5), store, budget=1)
     d.ask("earlier task")
-    marker = store.read_events()[-1].id
+    marker = log(store).read()[-1].id
     # A new task starts its allowance afresh from its own marker.
     assert d.ask("new task", since_event_id=marker).confidence == "high"
 
 
+def test_the_budget_is_per_work_item(store: StateStore) -> None:
+    # Consults in one task never use up another's allowance (L9).
+    desk(ScriptedClient([GOOD]), store, item="a", budget=1).ask("one")
+    assert desk(ScriptedClient([GOOD]), store, item="b", budget=1).ask("two")
+    with pytest.raises(BudgetExhausted):
+        desk(ScriptedClient([GOOD]), store, item="a", budget=1).ask("three")
+
+
 def test_default_budget_is_small() -> None:
     assert DEFAULT_BUDGET <= 5  # L9: do not let this become a second subsystem