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_planner.py

@@ -23,7 +23,7 @@ from nisse_dev.control import (
 from nisse_dev.llm import BudgetExhausted, RoleMap
 from nisse_dev.oplog import OpLog
 from nisse_dev.planner import PLANNER_TOOLS, LLMPlanningAgent
-from nisse_dev.state import StateStore
+from nisse_dev.state import StateStore, Transcript
 from nisse_dev.transport import InMemoryTransport
 
 ROLES = RoleMap(
@@ -64,6 +64,13 @@ def plan_call(content: str, gate: str = "arch") -> ToolCall:
     )
 
 
+ITEM = "t"  # the work item the unit tests plan in
+
+
+def log(store: StateStore) -> Transcript:
+    return store.transcript(ITEM, "planner")
+
+
 @pytest.fixture
 def store(tmp_path: Path) -> StateStore:
     return StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
@@ -71,8 +78,8 @@ def store(tmp_path: Path) -> StateStore:
 
 def test_submit_plan_tool_call_becomes_submit_plan(store: StateStore) -> None:
     client = ScriptedClient([[plan_call("step 1: create src/app.py")]])
-    agent = LLMPlanningAgent(client, store, ROLES)
-    action = agent.plan("arch", "demo")
+    agent = LLMPlanningAgent(client, ROLES)
+    action = agent.plan(log(store), "arch", "demo")
     assert action == SubmitPlan("step 1: create src/app.py")
 
 
@@ -88,13 +95,13 @@ def test_ask_human_tool_call_becomes_ask_human(store: StateStore) -> None:
             ]
         ]
     )
-    action = LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+    action = LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
     assert action == AskHuman("postgres or sqlite?")
 
 
 def test_planner_role_and_tools_are_used(store: StateStore) -> None:
     client = ScriptedClient([[plan_call("plan")]])
-    LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+    LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
     call = client.calls[0]
     assert call["model"] == "anthropic/claude-opus-5"  # never the executor
     assert [t["function"]["name"] for t in call["tools"]] == [
@@ -113,8 +120,8 @@ def test_model_output_is_appended_to_the_log(store: StateStore) -> None:
     client = ScriptedClient(
         [[AssistantText(text="thinking out loud", model="m"), plan_call("the plan")]]
     )
-    LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
-    kinds = [type(e.event).__name__ for e in store.read_events()]
+    LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
+    kinds = [type(e.event).__name__ for e in log(store).read()]
     assert kinds == ["AssistantText", "ToolCall", "ToolResult"]
 
 
@@ -122,8 +129,8 @@ def test_gate_tool_call_is_answered_in_the_log(store: StateStore) -> None:
     # submit_plan ends the turn and has no natural result, but a tool call
     # left dangling makes the next render invalid for the provider.
     client = ScriptedClient([[plan_call("the plan")]])
-    LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
-    events = [e.event for e in store.read_events()]
+    LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
+    events = [e.event for e in log(store).read()]
     assert [type(e).__name__ for e in events] == ["ToolCall", "ToolResult"]
     assert events[1].call_id == events[0].call_id
     assert "posted for approval" in events[1].result
@@ -137,7 +144,7 @@ def test_prose_only_turn_retries_once_then_raises(store: StateStore) -> None:
         ]
     )
     with pytest.raises(PlanningError, match="no submit_plan or ask_human"):
-        LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+        LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
     assert len(client.calls) == 2
     assert "did not call a tool" in client.calls[1]["system"]
 
@@ -146,7 +153,7 @@ def test_retry_succeeds_after_prose(store: StateStore) -> None:
     client = ScriptedClient(
         [[AssistantText(text="prose", model="m")], [plan_call("the real plan")]]
     )
-    action = LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+    action = LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
     assert action == SubmitPlan("the real plan")
 
 
@@ -154,13 +161,15 @@ def test_malformed_tool_arguments_are_rejected(store: StateStore) -> None:
     blank = ToolCall(call_id="c", tool="submit_plan", arguments={"content": "   "})
     client = ScriptedClient([[blank], [blank]])
     with pytest.raises(PlanningError):
-        LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+        LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
 
 
 def test_planner_sees_prior_transcript(store: StateStore) -> None:
-    store.append_event(UserMessage(text="use demo", source="transport:@don"))
+    store.transcript(ITEM, "operator").append(
+        UserMessage(text="use demo", source="transport:@don")
+    )
     client = ScriptedClient([[plan_call("plan")]])
-    LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+    LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
     seen = [e.event for e in client.calls[0]["events"]]
     assert UserMessage(text="use demo", source="transport:@don") in seen
 
@@ -171,7 +180,7 @@ def test_planner_sees_prior_transcript(store: StateStore) -> None:
 def build(tmp_path: Path, client: ScriptedClient) -> tuple[Orchestrator, StateStore]:
     store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
     transport = InMemoryTransport()
-    agent = LLMPlanningAgent(client, store, ROLES)
+    agent = LLMPlanningAgent(client, ROLES)
     orch = Orchestrator(store, transport, agent, operators={"don"}, roles=ROLES)
     orch.start()
     return orch, store, transport
@@ -186,7 +195,10 @@ def test_use_project_produces_llm_plan_and_transcript(tmp_path: Path) -> None:
     assert request.kind == "approval_request"
     assert "create app.py" in request.text
 
-    events = [e.event for e in store.read_events()]
+    # The work item's own events: `use demo` was said while idle, and is
+    # carried into the item it opened (D1).
+    item = store.active_item()
+    events = [e.event for e in store.transcript(item.id, "operator").read()]
     kinds = [type(e).__name__ for e in events]
     assert kinds == [
         "UserMessage",
@@ -237,7 +249,7 @@ def test_operator_can_recover_from_a_planning_failure(tmp_path: Path) -> None:
 
 def test_operator_can_recover_after_a_stopped_milestone(tmp_path: Path) -> None:
     class StoppedExecutor:
-        def run(self, milestone: int) -> Any:
+        def run(self, transcript: object, milestone: int) -> Any:
             from nisse_dev.executor import ExecutorOutcome
 
             return ExecutorOutcome("escalate", "tests failed twice")
@@ -248,7 +260,7 @@ def test_operator_can_recover_after_a_stopped_milestone(tmp_path: Path) -> None:
     orch = Orchestrator(
         store,
         transport,
-        LLMPlanningAgent(client, store, ROLES),
+        LLMPlanningAgent(client, ROLES),
         operators={"don"},
         roles=ROLES,
         executor=StoppedExecutor(),
@@ -295,5 +307,5 @@ def test_budget_exhaustion_is_not_retried(store: StateStore) -> None:
 
     client = BrokeClient()
     with pytest.raises(BudgetExhausted):
-        LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+        LLMPlanningAgent(client, ROLES).plan(log(store), "arch", "demo")
     assert client.calls == 1  # not two