feat(gateway): restore Gate Set B delegation-time guards

PARENT_NOT_CLAIMED: Choreographer.delegate now enforces that the parent
task is in_progress AND assigned to the calling PM before allowing
subtask creation. Pre-gateway this was implicit (orchestrator only
spawned PMs after they claimed their parent); the gateway exposes
delegate as a first-class verb so the gate must be explicit.

SUBTASK_CAP: hard-blocks delegation when the parent already has 12
subtasks. Pre-gateway never had this cap because PMs naturally never
created more than a handful per spawn cycle; with delegate as a verb
agents can loop, so a cap is needed.

The _delegate_guard helper was split into _delegate_role_guards,
_delegate_static_guards, and _delegate_lifecycle_guards to keep each
piece below the PLR0911 return-count threshold and make the layered
gating explicit.

Pre-gateway reference: implicit in roboco/runtime/orchestrator.py
spawn flow; restored here as explicit server-side enforcement.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

roboco/services/gateway/choreographer.py

@@ -950,6 +950,10 @@ class Choreographer:
             context_briefing=await self._briefing_for(pm_agent_id, parent_task_id),
         )
 
+    # Gate Set B subtask cap (pre-gateway implicit, made explicit here).
+    # Soft warn at 8, hard block at 13. Cap enforced by ``_subtask_cap_guard``.
+    _SUBTASK_HARD_CAP: int = 12
+
     async def _delegate_guard(
         self,
         pm_agent_id: UUID,
@@ -959,8 +963,27 @@ class Choreographer:
         inputs: DelegateInputs,
     ) -> Envelope | None:
         """Return rejection Envelope if a delegate precondition fails; else None."""
-        from roboco.seeds.initial_data import AGENT_UUIDS
+        if guard := await self._delegate_role_guards(
+            pm_agent_id, parent_task_id, agent, inputs
+        ):
+            return guard
+        if guard := await self._delegate_static_guards(
+            pm_agent_id, parent_task_id, parent, inputs
+        ):
+            return guard
+        # Gate Set B: PARENT_NOT_CLAIMED + SUBTASK_CAP
+        return await self._delegate_lifecycle_guards(
+            pm_agent_id, parent_task_id, parent
+        )
 
+    async def _delegate_role_guards(
+        self,
+        pm_agent_id: UUID,
+        parent_task_id: UUID,
+        agent: Any,
+        inputs: DelegateInputs,
+    ) -> Envelope | None:
+        """Role + delegation-chain guards (the original two)."""
         if agent is None or agent.role not in ("cell_pm", "main_pm"):
             return Envelope.not_authorized(
                 message="only cell_pm or main_pm may delegate",
@@ -978,6 +1001,18 @@ class Choreographer:
                 ),
                 context_briefing=await self._briefing_for(pm_agent_id, parent_task_id),
             )
+        return None
+
+    async def _delegate_static_guards(
+        self,
+        pm_agent_id: UUID,
+        parent_task_id: UUID,
+        parent: Any,
+        inputs: DelegateInputs,
+    ) -> Envelope | None:
+        """Slug / project_id / enum guards. Pure data-shape checks."""
+        from roboco.seeds.initial_data import AGENT_UUIDS
+
         if inputs.assigned_to not in AGENT_UUIDS:
             return Envelope.invalid_state(
                 message=f"unknown agent slug: {inputs.assigned_to!r}",
@@ -1000,6 +1035,61 @@ class Choreographer:
             )
         return None
 
+    async def _delegate_lifecycle_guards(
+        self,
+        pm_agent_id: UUID,
+        parent_task_id: UUID,
+        parent: Any,
+    ) -> Envelope | None:
+        """Gate Set B: PARENT_NOT_CLAIMED + SUBTASK_CAP.
+
+        Pre-gateway, the orchestrator enforced both implicitly: a PM only
+        ever called task_create after the orchestrator spawned them
+        post-claim, and naturally never created more than a handful of
+        subtasks in one spawn cycle.
+
+        With the gateway exposing ``delegate`` as a first-class verb,
+        these gates must be explicit.
+        """
+        if str(parent.status) != "in_progress":
+            return Envelope.invalid_state(
+                message=(
+                    f"parent task {parent_task_id} is in {parent.status}; "
+                    "must be in_progress to accept subtasks"
+                ),
+                remediate=(
+                    f"call i_will_plan(parent_task_id='{parent_task_id}',"
+                    " plan='...') before delegating subtasks"
+                ),
+                context_briefing=await self._briefing_for(pm_agent_id, parent_task_id),
+            )
+        if parent.assigned_to != pm_agent_id:
+            return Envelope.not_authorized(
+                message=(
+                    f"parent task {parent_task_id} is assigned to "
+                    f"{parent.assigned_to}, not you"
+                ),
+                remediate=(
+                    f"call i_will_plan(parent_task_id='{parent_task_id}',"
+                    " plan='...') to claim before delegating subtasks"
+                ),
+                context_briefing=await self._briefing_for(pm_agent_id, parent_task_id),
+            )
+        existing = await self.task.get_subtasks(parent_task_id)
+        if len(existing) >= self._SUBTASK_HARD_CAP:
+            return Envelope.invalid_state(
+                message=(
+                    f"parent already has {len(existing)} subtasks; "
+                    f"cap is {self._SUBTASK_HARD_CAP}"
+                ),
+                remediate=(
+                    "consolidate or split into a separate parent task before"
+                    " adding more subtasks"
+                ),
+                context_briefing=await self._briefing_for(pm_agent_id, parent_task_id),
+            )
+        return None
+
     @staticmethod
     def _resolve_delegate_enums(inputs: DelegateInputs) -> tuple[Any, Any, Any]:
         """Convert string inputs to Team/TaskType/Complexity enums.

tests/unit/gateway/test_choreographer_delegate_guards.py

@@ -0,0 +1,237 @@
+"""Gate Set B: delegation-time guards in Choreographer.delegate.
+
+Pre-gateway behavior: a PM could only call ``task_create`` while spawned
+in-context, which only happened after the orchestrator saw them claim
+and start a parent task. That implicit gate is restored explicitly here:
+
+- PARENT_NOT_CLAIMED: parent must be in_progress AND assigned_to PM.
+- SUBTASK_CAP: 8 children = soft warn (allowed), >12 = hard block.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+from unittest.mock import AsyncMock, MagicMock
+from uuid import uuid4
+
+import pytest
+from roboco.services.gateway.choreographer import (
+    Choreographer,
+    ChoreographerDeps,
+    DelegateInputs,
+)
+
+
+def _make_deps(**overrides: Any) -> ChoreographerDeps:
+    base: dict[str, Any] = {
+        "task": AsyncMock(),
+        "work_session": AsyncMock(),
+        "git": AsyncMock(),
+        "a2a": AsyncMock(),
+        "journal": AsyncMock(),
+        "audit": AsyncMock(),
+        "evidence_repo": AsyncMock(),
+    }
+    base.update(overrides)
+    repo = base["evidence_repo"]
+    for method in (
+        "list_unread_a2a",
+        "list_unread_mentions",
+        "list_pending_notifications",
+        "task_metadata_gaps",
+        "recent_team_activity",
+        "blockers_in_lane",
+        "journal_highlights_for_task",
+    ):
+        getattr(repo, method).return_value = []
+    return ChoreographerDeps(**base)
+
+
+def _delegate_inputs() -> DelegateInputs:
+    return DelegateInputs(
+        title="Implement endpoint",
+        description="Add /v1/foo endpoint with tests",
+        assigned_to="be-dev-1",
+        team="backend",
+    )
+
+
+@pytest.mark.asyncio
+async def test_delegate_blocks_when_parent_not_in_progress() -> None:
+    """Parent in 'pending' status (PM never called i_will_plan) blocks delegate."""
+    pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="pending",
+        assigned_to=pm_id,
+    )
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = []
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] == "invalid_state"
+    assert "i_will_plan" in body["remediate"]
+    task_svc.create_subtask.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_delegate_blocks_when_parent_assigned_to_other_agent() -> None:
+    """Parent claimed by a different PM cannot be delegated against by us."""
+    pm_id = uuid4()
+    other_pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="in_progress",
+        assigned_to=other_pm_id,
+    )
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = []
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] == "not_authorized"
+    assert "i_will_plan" in body["remediate"]
+    task_svc.create_subtask.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_delegate_allows_when_parent_in_progress_and_owned() -> None:
+    pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="in_progress",
+        assigned_to=pm_id,
+    )
+    new_task = MagicMock(id=uuid4())
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = []
+    task_svc.create_subtask.return_value = new_task
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] is None
+    assert body["status"] == "created"
+    task_svc.create_subtask.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_delegate_blocks_when_subtask_cap_exceeded() -> None:
+    """13+ subtasks = hard block (cap is 12)."""
+    pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="in_progress",
+        assigned_to=pm_id,
+    )
+    too_many = [MagicMock(id=uuid4()) for _ in range(13)]
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = too_many
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] == "invalid_state"
+    assert "13" in body["message"] or "consolidate" in body["remediate"].lower()
+    task_svc.create_subtask.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_delegate_allows_when_subtask_cap_within_soft_zone() -> None:
+    """8-12 subtasks: warn-but-allow."""
+    pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="in_progress",
+        assigned_to=pm_id,
+    )
+    many = [MagicMock(id=uuid4()) for _ in range(10)]
+    new_task = MagicMock(id=uuid4())
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = many
+    task_svc.create_subtask.return_value = new_task
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] is None
+    task_svc.create_subtask.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_delegate_allows_at_zero_subtasks() -> None:
+    """Empty subtask list is the common case."""
+    pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="in_progress",
+        assigned_to=pm_id,
+    )
+    new_task = MagicMock(id=uuid4())
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = []
+    task_svc.create_subtask.return_value = new_task
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] is None
+
+
+@pytest.mark.asyncio
+async def test_delegate_blocks_at_exact_cap_plus_one() -> None:
+    """Cap is 12; 13th attempt blocks."""
+    pm_id = uuid4()
+    parent_id = uuid4()
+    parent = MagicMock(
+        id=parent_id,
+        project_id=uuid4(),
+        status="in_progress",
+        assigned_to=pm_id,
+    )
+    # Already 12 children — adding the 13th must be blocked.
+    twelve = [MagicMock(id=uuid4()) for _ in range(12)]
+    task_svc = AsyncMock()
+    task_svc.get.return_value = parent
+    task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = twelve
+    deps = _make_deps(task=task_svc)
+    c = Choreographer(deps)
+
+    env = await c.delegate(pm_id, parent_id, _delegate_inputs())
+    body = env.as_dict()
+    assert body["error"] == "invalid_state"
+    task_svc.create_subtask.assert_not_awaited()

tests/unit/gateway/test_choreographer_pm_extras.py

@@ -166,11 +166,17 @@ async def test_delegate_main_pm_to_cell_pm_creates_subtask() -> None:
     main_pm_id = uuid4()
     parent_id = uuid4()
     project_id = uuid4()
-    parent = MagicMock(id=parent_id, project_id=project_id)
+    parent = MagicMock(
+        id=parent_id,
+        project_id=project_id,
+        status="in_progress",
+        assigned_to=main_pm_id,
+    )
     new_task = MagicMock(id=uuid4())
     task_svc = AsyncMock()
     task_svc.get.return_value = parent
     task_svc.agent_for.return_value = MagicMock(role="main_pm", team="main_pm")
+    task_svc.get_subtasks.return_value = []
     task_svc.create_subtask.return_value = new_task
     deps = _make_deps(task=task_svc)
     c = Choreographer(deps)
@@ -198,11 +204,17 @@ async def test_delegate_cell_pm_to_team_dev_creates_subtask() -> None:
     cell_pm_id = uuid4()
     parent_id = uuid4()
     project_id = uuid4()
-    parent = MagicMock(id=parent_id, project_id=project_id)
+    parent = MagicMock(
+        id=parent_id,
+        project_id=project_id,
+        status="in_progress",
+        assigned_to=cell_pm_id,
+    )
     new_task = MagicMock(id=uuid4())
     task_svc = AsyncMock()
     task_svc.get.return_value = parent
     task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
+    task_svc.get_subtasks.return_value = []
     task_svc.create_subtask.return_value = new_task
     deps = _make_deps(task=task_svc)
     c = Choreographer(deps)