core/agent+tools+cli: number todos by listing order, not the internal id

tests/test_agent/test_todo_stack.py

@@ -66,6 +66,29 @@ def test_ids_reuse_after_pop() -> None:
     assert g3.items[0].id == "t3"
 
 
+def test_render_numbers_follow_listing_order() -> None:
+    """Numbers are listing positions (TOP group first), never the stored ids."""
+    stack = TodoStack()
+    root = stack.push_group(["root", "sibling"])  # stored ids t1, t2
+    _ = stack.push_group(["child"])  # stored id t3
+    listing = stack.render()
+    assert "  [ ] 1. child" in listing
+    assert "  [ ] 2. root" in listing
+    assert "  [ ] 3. sibling" in listing
+    assert "t1" not in listing
+    assert "t3" not in listing
+
+    # update(1) is the first item the listing shows — the one stored as t3.
+    updated = stack.update(1, status="done")
+    assert updated.id == "t3"
+    assert updated.title == "child"
+    assert updated.status == "done"
+    assert root.items[0].status == "pending"
+
+    with pytest.raises(ValueError, match="no todo item 4"):
+        stack.update(4, status="done")
+
+
 def test_push_is_group_not_per_task_stack() -> None:
     """Multi-title push is one group; pop removes the whole group."""
     stack = TodoStack()
@@ -94,11 +117,16 @@ def test_dfs_breakdown_with_groups() -> None:
     root = stack.push_group(["T1", "T2"])
     children = stack.push_group(["T1.1", "T1.2"])
     assert stack.depth == 2
-    stack.update(children.items[0].id, status="done")
-    stack.update(children.items[1].id, status="done")
+    # Numbers come from the listing: the pushed children are the TOP group → 1, 2.
+    stack.update(1, status="done")
+    stack.update(2, status="done")
+    assert [i.status for i in children.items] == ["done", "done"]
     _ = stack.pop()
     assert stack.depth == 1
-    stack.update(root.items[0].id, status="done")
+    # Children gone: the root group is the listing again → 1 is T1, 2 is T2.
+    stack.update(1, status="done")
+    assert root.items[0].status == "done"
+    assert root.items[1].status == "pending"
     _ = stack.push_group(["T2.1"])
     assert stack.depth == 2
     assert stack.top_group is not None
@@ -119,14 +147,14 @@ def test_single_title_still_one_group() -> None:
 def test_todo_stack_needs_review() -> None:
     stack = TodoStack()
     assert not stack.needs_review()
-    item = stack.push("work")
+    _ = stack.push("work")
     stack.begin_turn()
     # Non-empty + untouched → nag (open or hygiene).
     assert stack.needs_review()
     # Any todo_* access this turn suppresses end-of-turn nag, even with open items.
     stack.mark_touched()
     assert not stack.needs_review()
-    stack.update(item.id, status="done")
+    stack.update(1, status="done")
     stack.begin_turn()
     # Terminal-only stack: same gate (untouched only).
     assert stack.needs_review()
@@ -212,7 +240,7 @@ def test_inject_todo_nag_strategies() -> None:
 
 def test_todo_prompts_signal_undone_work() -> None:
     stack = TodoStack()
-    item = stack.push("open work")
+    _ = stack.push("open work")
     reminder = stack.turn_reminder_prompt()
     assert "[TODO OPEN WORK]" in reminder
     assert "Stack not empty" in reminder
@@ -223,9 +251,9 @@ def test_todo_prompts_signal_undone_work() -> None:
     assert "[TODO OPEN WORK]" in review
     assert "undone work" in review.lower() or "open item" in review.lower()
     assert "open work" in review
-    assert "t1:open work" in review or "open work" in review
+    assert "1. open work" in review  # the review embeds the numbered listing
 
-    stack.update(item.id, status="done")
+    stack.update(1, status="done")
     terminal_review = stack.review_prompt()
     assert "[TODO HYGIENE]" in terminal_review
     assert "done/cancelled" in terminal_review

tests/test_cli/test_display.py

@@ -174,28 +174,28 @@ async def test_pretty_todo_push(capsys: pytest.CaptureFixture[str]) -> None:
         )
     )
     result = (
-        "pushed group (depth=1) items=[a1]\n"
+        "pushed group (depth=1) items=[T1]\n"
         "(LIFO of groups: depth=1; TOP group = current breakdown level)\n"
         "group d=0 TOP:\n"
-        "  [ ] a1: T1"
+        "  [ ] 1. T1"
     )
     await render_events(_aiter([call, _result(result)]))
     out = capsys.readouterr().out
     assert "* Todo Push:" in out
-    assert "  [ ] a1: T1" in out
+    assert "  [ ] 1. T1" in out
     assert "[tool]" not in out
 
 
 async def test_pretty_todo_batch_merges_to_one_stack(capsys: pytest.CaptureFixture[str]) -> None:
     """A batch of todo calls: one summary line, then the last result's stack."""
-    stack = "(LIFO of groups: depth=1; TOP group = current breakdown level)\ngroup d=0 TOP:\n  [ ] a1: T1"
+    stack = "(LIFO of groups: depth=1; TOP group = current breakdown level)\ngroup d=0 TOP:\n  [ ] 1. T1"
     await render_events(
         _aiter(
             [
                 _pretty_call("todo_push", '{"titles": ["T1"]}'),
-                _pretty_call("todo_update", '{"item_id": "a1", "status": "done"}'),
-                _result(f"pushed group (depth=1) items=[a1]\n{stack}"),
-                _result(f"updated a1 → done: T1\n{stack}"),
+                _pretty_call("todo_update", '{"number": 1, "status": "done"}'),
+                _result(f"pushed group (depth=1) items=[T1]\n{stack}"),
+                _result(f"updated 1 → done: T1\n{stack}"),
             ]
         )
     )
@@ -206,14 +206,14 @@ async def test_pretty_todo_batch_merges_to_one_stack(capsys: pytest.CaptureFixtu
     # Only the last result is printed, so the stack renders once.
     assert out.count("group d=0 TOP:") == 1
     assert "pushed group" not in out
-    assert "updated a1 → done: T1" in out
+    assert "updated 1 → done: T1" in out
 
 
 async def test_pretty_todo_batch_mixed_with_other_tool_stays_per_call(
     capsys: pytest.CaptureFixture[str],
 ) -> None:
     """A batch holding a non-todo call keeps one line (and stack) per todo call."""
-    stack = "group d=0 TOP:\n  [ ] a1: T1"
+    stack = "group d=0 TOP:\n  [ ] 1. T1"
     await render_events(
         _aiter(
             [
@@ -867,13 +867,13 @@ async def test_pretty_vcs_kind_branch_and_diff(capsys: pytest.CaptureFixture[str
 
 
 async def test_pretty_todo_list_pop_and_clear(capsys: pytest.CaptureFixture[str]) -> None:
-    stack = "  [ ] a1: T1\n  [x] a2: T2"
+    stack = "  [ ] 1. T1\n  [x] 2. T2"
     await render_events(_aiter([_pretty_call("todo_list", "{}"), _result(stack)]))
     out = capsys.readouterr().out
     assert "* Todo List:" in out
-    assert "  [ ] a1: T1" in out
+    assert "  [ ] 1. T1" in out
 
-    await render_events(_aiter([_pretty_call("todo_pop", "{}"), _result(f"popped TOP group (a1:T1)\n{stack}")]))
+    await render_events(_aiter([_pretty_call("todo_pop", "{}"), _result(f"popped TOP group (T1)\n{stack}")]))
     out = capsys.readouterr().out
     assert "* Todo Pop:" in out
 

tests/test_cli/test_readline_setup.py

@@ -194,9 +194,9 @@ def test_complete_slash_args_from_registry(tmp_path: object) -> None:
 
     state.todo_stack = TodoStack()
     _ = state.todo_stack.push_group(["alpha", "beta"])
-    ids = complete_slash_args(state, "/todos", "t", prior_args=["done"])
-    assert "t1" in ids
-    assert "t2" in ids
+    numbers = complete_slash_args(state, "/todos", "", prior_args=["done"])
+    assert numbers == ["1", "2"]
+    assert complete_slash_args(state, "/todos", "2", prior_args=["done"]) == ["2"]
 
     state.remember_session_ids([3, 12, 40])
     assert complete_slash_args(state, "/resume", "1") == ["12"]

tests/test_cli/test_repl_commands.py

@@ -757,3 +757,26 @@ async def test_btw_read_notice_states_read_only_scope(
     assert "read-only" in notice.body
     assert "not saved" in notice.body
     assert "[notice] aside: read tools" in capsys.readouterr().out
+
+
+async def test_todos_update_takes_a_listing_number(state: ReplState, capsys: pytest.CaptureFixture[str]) -> None:
+    assert await handle_slash(state, "/todos push first; second") is True
+    out = capsys.readouterr().out
+    assert "pushed group depth=1 items=[first, second]" in out
+    assert "  [ ] 1. first" in out
+    assert "  [ ] 2. second" in out
+    assert "t1" not in out
+
+    assert await handle_slash(state, "/todos done 2") is True
+    out = capsys.readouterr().out
+    assert "updated 2 → done" in out
+    assert "  [x] 2. second" in out
+
+    # The stored id is not an address: only listing numbers are.
+    assert await handle_slash(state, "/todos done t1") is True
+    assert "takes an item number from the list" in capsys.readouterr().out
+    assert await handle_slash(state, "/todos done 7") is True
+    assert "no todo item 7" in capsys.readouterr().out
+
+    assert await handle_slash(state, "/todos pop") is True
+    assert "popped TOP group (first, second)" in capsys.readouterr().out

tests/test_tools/test_todo_session.py

@@ -101,6 +101,33 @@ async def test_session_on_todo_change_fires() -> None:
     assert hits == ["session"]
 
 
+async def test_todo_update_uses_listing_numbers() -> None:
+    store = MemoryViewStore({})
+    session = SessionState(session_id="numbers", data=session_data_view(store=store))
+    registry = ToolRegistry(list(TODO_TOOLS), session_state=session)
+
+    out = await registry.execute("todo_push", '{"titles": ["root"]}')
+    assert "pushed group (depth=1) items=[root]" in out
+    out = await registry.execute("todo_push", '{"titles": ["child"]}')
+    assert "pushed group (depth=2) items=[child]" in out
+    # TOP group first; the stored ids stay out of every result.
+    assert "  [ ] 1. child" in out
+    assert "  [ ] 2. root" in out
+    assert "t1" not in out and "t2" not in out
+
+    numbered = await registry.execute("todo_update", '{"number": 2, "status": "done"}')
+    assert "updated 2 → done: root" in numbered
+    assert "  [x] 2. root" in numbered
+
+    stale = await registry.execute("todo_update", '{"number": 9, "status": "done"}')
+    assert stale.startswith("error: no todo item 9")
+    shaped = await registry.execute("todo_update", '{"number": "first"}')
+    assert shaped.startswith("error: `todo_update` expects `number`")
+
+    popped = await registry.execute("todo_pop", "{}")
+    assert "popped TOP group (child); new top group=[root]" in popped
+
+
 async def test_todo_without_session_errors() -> None:
     registry = ToolRegistry(list(TODO_TOOLS))
     out = await registry.execute("todo_list", "{}")