core/agent: agent-facing [TODO OPEN] review nag

src/plyngent/agent/todo_stack.py

@@ -174,15 +174,19 @@ class TodoStack:
         return "\n".join(lines)
 
     def review_prompt(self) -> str:
-        return (
-            "Todo stack review (internal control — not a human message).\n"
-            "This is a LIFO stack of **task groups** (not a queue of single tasks).\n"
-            "push([T1,T2]) creates one group of siblings; push([T1.1,T1.2]) pushes a "
-            "child group; pop removes the whole top group. Update items by id; "
-            "pop when a breakdown level is finished. Open work remains and you "
-            "did not call any todo_* tools this turn.\n\n"
-            f"Current stack:\n{self.render()}"
-        )
+        """Compact, model-facing nag: open work still exists this turn."""
+        open_items = self.open_items()
+        n_open = len(open_items)
+        n_groups = self.depth
+        lines = [
+            f"[TODO OPEN] {n_open} open item(s) across {n_groups} group(s) "
+            f"(not empty). You did not call todo_* this turn.",
+            "Tools: todo_list | todo_push(titles=[...]) | todo_update | todo_pop | todo_clear",
+            "Rules: TOP group = current level; push=one sibling group; pop=remove whole TOP group.",
+            "Act on open work before ending (finish/pop TOP, or push child tasks). Stack:",
+            self.render(),
+        ]
+        return "\n".join(lines)
 
     def _existing_numeric_ids(self) -> list[int]:
         """Numeric suffixes of ids that look like ``tN`` (for counter reuse)."""

tests/test_agent/test_todo_stack.py

@@ -152,11 +152,11 @@ async def test_todo_tools_and_persist(tmp_path: object) -> None:
         stack = TodoStack()
         set_todo_stack(stack, on_change=None)
         registry = ToolRegistry(list(TODO_TOOLS))
-        out = await registry.execute("todo_push", '{"titles": "T1\\nT2"}')
+        out = await registry.execute("todo_push", '{"titles": ["T1", "T2"]}')
         assert "group" in out.lower() or "pushed" in out
         assert stack.depth == 1
         assert [i.title for i in stack.groups[0].items] == ["T1", "T2"]
-        _ = await registry.execute("todo_push", '{"titles": "T1.1; T1.2"}')
+        out = await registry.execute("todo_push", '{"titles": ["T1", "T2"]}')
         assert stack.depth == 2
         out3 = await registry.execute("todo_pop", "{}")
         assert "popped" in out3
@@ -193,7 +193,7 @@ class ScriptedClient:
         self.calls += 1
         text = "ok" if self.calls > 1 else "done without todos"
         for msg in param.messages:
-            if isinstance(msg, DeveloperChatMessage) and "Todo stack review" in msg.content:
+            if isinstance(msg, DeveloperChatMessage) and "[TODO OPEN]" in msg.content:
                 text = "reviewed stack"
                 break
         return ChatCompletionResponse(
@@ -232,7 +232,7 @@ async def test_loop_injects_todo_review_when_untouched() -> None:
         async for _event in agent.run("do stuff"):
             pass
         assert client.calls >= 2
-        assert any(isinstance(m, DeveloperChatMessage) and "Todo stack review" in m.content for m in agent.messages)
-        assert not any(isinstance(m, UserChatMessage) and "Todo stack review" in m.content for m in agent.messages)
+        assert any(isinstance(m, DeveloperChatMessage) and "[TODO OPEN]" in m.content for m in agent.messages)
+        assert not any(isinstance(m, UserChatMessage) and "[TODO OPEN]" in m.content for m in agent.messages)
     finally:
         set_todo_stack(None)