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_executor.py

@@ -14,7 +14,7 @@ from nisse_dev.canonical import (
 from nisse_dev.executor import LLMExecutor
 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
 from nisse_dev.tools import Workspace
 
 ROLES = RoleMap(
@@ -66,8 +66,26 @@ def ws(tmp_path: Path) -> Workspace:
     return Workspace(tmp_path / "work", timeout_s=10)
 
 
-def build(client: Any, store: StateStore, ws: Workspace, **kw: Any) -> LLMExecutor:
-    return LLMExecutor(client, store, ROLES, ws, **kw)
+ITEM = "t"  # the work item these tests run in
+
+
+def log(store: StateStore) -> Transcript:
+    return store.transcript(ITEM, "executor")
+
+
+class Bound:
+    """An executor run in the test's work item, as the orchestrator runs it."""
+
+    def __init__(self, executor: LLMExecutor, store: StateStore) -> None:
+        self.executor = executor
+        self.store = store
+
+    def run(self, milestone: int) -> Any:
+        return self.executor.run(log(self.store), milestone)
+
+
+def build(client: Any, store: StateStore, ws: Workspace, **kw: Any) -> Bound:
+    return Bound(LLMExecutor(client, ROLES, ws, **kw), store)
 
 
 def test_tool_calls_are_executed_and_results_logged(
@@ -84,7 +102,7 @@ def test_tool_calls_are_executed_and_results_logged(
     assert outcome.status == "completed"
     assert outcome.note == "wrote the file"
     assert (ws.root / "app.py").read_text() == "print(1)\n"
-    kinds = [type(e.event).__name__ for e in store.read_events()]
+    kinds = [type(e.event).__name__ for e in log(store).read()]
     assert kinds == ["ToolCall", "ToolResult", "ToolCall", "ToolResult"]
 
 
@@ -138,7 +156,7 @@ def test_finishing_without_any_work_is_refused_once(
     assert (ws.root / "a.py").exists()  # the refusal produced actual work
     [refusal] = [
         e.event
-        for e in store.read_events()
+        for e in log(store).read()
         if isinstance(e.event, ToolResult) and e.event.call_id == "f1"
     ]
     assert not refusal.success
@@ -165,7 +183,7 @@ def test_calls_after_finish_are_not_run(store: StateStore, ws: Workspace) -> Non
     assert not (ws.root / "b.py").exists()
     [late] = [
         e.event
-        for e in store.read_events()
+        for e in log(store).read()
         if isinstance(e.event, ToolResult) and e.event.call_id == "late"
     ]
     assert "finish had already ended the milestone" in late.result
@@ -183,7 +201,7 @@ def test_an_invented_tool_counts_toward_escalation(
     outcome = build(client, store, ws, failure_limit=2).run(milestone=1)
     assert outcome.status == "escalate"
     assert len(client.calls) == 2
-    results = [e.event for e in store.read_events() if isinstance(e.event, ToolResult)]
+    results = [e.event for e in log(store).read() if isinstance(e.event, ToolResult)]
     assert "no such tool: chat" in results[0].result
     assert "finish" in results[0].result  # it is told what does exist
 
@@ -280,7 +298,7 @@ def test_multiple_calls_in_one_turn_all_run(store: StateStore, ws: Workspace) ->
     build(client, store, ws).run(milestone=1)
     assert (ws.root / "one.txt").exists() and (ws.root / "two.txt").exists()
     results = [
-        e.event for e in store.read_events() if type(e.event).__name__ == "ToolResult"
+        e.event for e in log(store).read() if type(e.event).__name__ == "ToolResult"
     ]
     assert {r.call_id for r in results} == {"a", "b", "fin"}
 
@@ -293,7 +311,7 @@ class StubDesk:
         self._answer = answer
         self._error = error
 
-    def ask(self, question: str, **kw: Any) -> Any:
+    def ask(self, transcript: Any, question: str, **kw: Any) -> Any:
         self.asked.append(question)
         if self._error is not None:
             raise self._error
@@ -336,7 +354,7 @@ def test_ask_expert_answer_comes_back_as_a_tool_result(
 
     assert desk.asked == ["sqlite or postgres?"]
     results = [
-        e.event for e in store.read_events() if type(e.event).__name__ == "ToolResult"
+        e.event for e in log(store).read() if type(e.event).__name__ == "ToolResult"
     ]
     assert "prefer sqlite here" in results[0].result
 
@@ -372,7 +390,7 @@ def test_exhausted_budget_is_reported_to_the_model_not_raised(
 
     assert outcome.status == "completed"  # it got on with the work
     results = [
-        e.event for e in store.read_events() if type(e.event).__name__ == "ToolResult"
+        e.event for e in log(store).read() if type(e.event).__name__ == "ToolResult"
     ]
     assert not results[0].success
     assert "budget" in results[0].result