feat: bounded subagent delegation (v5)

Coordinator parts gain three enforced bounds, validated in
validate_parts and carried through the coordinator_parts JSON
(no schema change): timeout_seconds (1..86400, per-attempt
wall clock from coordinator start; the coordinator poll loop
cancels only that child with the same cancel mechanism as
the global timeout, other parts keep waiting, audit
coordinator_child_bound_exceeded), on_failure fail|tolerate
(tolerated failures do not fail the coordinator, are named
in the report head, and their failed children are not
requeued on coordinator re-run while interrupted children
still are), and result_chars (0..2000, default 500, enforced
in build_report; the 4000-char report writeback cap still
applies). evaluate_outcome is the single outcome rule used
by both build_report and the worker error text, so tolerated
failures never leak into the coordinator failure reason.
Unknown part names fail closed.

Deliberately NOT added, after reading the execution layer:
per-part token/cost budget (cost is recorded only on
completion, so a running child's spend is unobservable and
creator quota is monthly, not per part), per-part round cap
(normal tasks have no per-task round cap in the worker),
and write-scope isolation (sandbox is per-project worktree,
a scope string in a prompt would be an instruction, not a
guarantee). Tests: test_delegation_bounds.py (8 tests).

cloud/tests/test_coordinator.py

@@ -95,7 +95,10 @@ class ValidatePartsTestCase(unittest.TestCase):
         self.assertIsNone(err)
         self.assertEqual(parts, [{"name": "a", "prompt": "做 a",
                                   "model": None, "effort": None,
-                                  "executor": None}])
+                                  "executor": None,
+                                  "timeout_seconds": None,
+                                  "on_failure": "fail",
+                                  "result_chars": 500}])
 
     def test_valid_with_options(self):
         parts, err = validate_parts([{