[F007] choreographer: cell-level unchanged-PR re-submit loop-stopper for submit_up

The root loop-stopper (F016) was root-only; a weak cell PM could re-submit
the unchanged cell->root PR after a pr_fail and loop awaiting_pr_review ->
pr_fail forever (the cell analogue of the 2026-06-27 root loop).

pr_fail stamps the assembled PR's head SHA into notes_structured.pr_review
.head_sha for cell AND root gate tasks alike (the capture is gate-verb-
level, not root-level), so the same structural refusal applies to submit_up:
if the cell PR's current head SHA equals the SHA the last pr_fail recorded,
no new dev work landed on the cell branch -> the diff is byte-identical ->
refuse, do not re-open the gate. Different SHA -> branch advanced -> allow.

- _submit_up_unchanged_pr_guard mirrors _submit_root_unchanged_pr_guard
  (cell-PM remediation: re-delegate to the dev + wait for re-assembly),
  wired into submit_up after _submit_up_guard passes.
- Renamed shared _current_root_pr_head_sha -> _current_pr_head_sha (both
  guards use it; the lookup was never root-specific).
- Every ambiguous case FAILS OPEN (no prior fail, no recorded sha, no
  pr_number, no resolvable project, git/closed-PR None) — only the exact-
  unchanged case is hard-blocked.

TDD red->green; ruff + mypy clean; F007+F016 guard suites green (15 passed).
This commit is contained in:
Renn F
2026-06-28 10:23:54 +02:00
parent 742e0ebfaf
commit 2ed7f5978f
2 changed files with 201 additions and 6 deletions
+57 -6
View File
@@ -5237,6 +5237,12 @@ class Choreographer:
# + subtasks-terminal + branch-present. None of these are modelled by
# the spec yet — keep them in the verb body.
guard = await self._submit_up_guard(pm_agent_id, task_id, t, notes)
# F007: the cell-level unchanged-PR loop-stopper. Only consult it once
# the state guard above has passed (ownership/tracing/branch all OK) —
# mirroring submit_root, a prior preflight reject short-circuits before
# the head-sha comparison runs.
if guard is None:
guard = await self._submit_up_unchanged_pr_guard(t, briefing)
if guard is not None:
guard.with_introspection(task=t, role=role_str)
return await self._emit_rejection(
@@ -5980,7 +5986,7 @@ class Choreographer:
recorded = pr_review.get("head_sha")
if not recorded:
return None
current = await self._current_root_pr_head_sha(t)
current = await self._current_pr_head_sha(t)
if current is None or current != recorded:
return None
return Envelope.invalid_state(
@@ -6001,13 +6007,16 @@ class Choreographer:
context_briefing=briefing,
)
async def _current_root_pr_head_sha(self, t: Any) -> str | None:
async def _current_pr_head_sha(self, t: Any) -> str | None:
"""Best-effort current head SHA of the task's assembled PR (fail-open).
The lookup the unchanged-PR gate compares against. Returns ``None`` on
every ambiguous case (no ``pr_number``, no resolvable project slug, a
git error, or a closed/missing PR) so the gate fails open rather than
wedging the PM only the exact-unchanged case is hard-blocked.
The lookup both unchanged-PR gates (submit_root F016 + submit_up F007)
compare against ``pr_fail`` stamps the head SHA for cell AND root
gate tasks alike (the capture is gate-verb-level, not root-level), so
one resolver serves both. Returns ``None`` on every ambiguous case (no
``pr_number``, no resolvable project slug, a git error, or a
closed/missing PR) so the gate fails open rather than wedging the PM
only the exact-unchanged case is hard-blocked.
"""
pr_number = getattr(t, "pr_number", None)
if not pr_number:
@@ -6026,6 +6035,48 @@ class Choreographer:
except Exception:
return None
async def _submit_up_unchanged_pr_guard(
self, t: Any, briefing: dict[str, Any]
) -> Envelope | None:
"""F007 — the cell-level analogue of ``_submit_root_unchanged_pr_guard``.
The root loop-stopper was root-only; a weak cell PM could re-submit the
unchanged cellroot PR after a ``pr_fail`` and loop
``awaiting_pr_review`` ``pr_fail`` forever. ``pr_fail`` stamps the
assembled PR's head SHA into ``notes_structured.pr_review.head_sha``
for cell gate tasks too (the capture is gate-verb-level), so the same
structural refusal applies: if the cell PR's current head SHA equals
the SHA the last ``pr_fail`` recorded, no new dev work landed on the
cell branch the diff is byte-identical refuse. Every ambiguous case
FAILS OPEN (shared ``_current_pr_head_sha``) only the exact-unchanged
case is hard-blocked; the rest fall through to the cell reviewer.
"""
pr_review = (getattr(t, "notes_structured", None) or {}).get("pr_review") or {}
if pr_review.get("verdict") != "failed":
return None
recorded = pr_review.get("head_sha")
if not recorded:
return None
current = await self._current_pr_head_sha(t)
if current is None or current != recorded:
return None
return Envelope.invalid_state(
message=(
"the assembled cell PR is unchanged since the last pr_fail"
f" (head {current[:7]}). No new dev work has landed on the"
" cell branch, so re-submitting would re-open the exact diff"
" the reviewer just rejected and loop straight back to"
" awaiting_pr_review."
),
remediate=(
"re-delegate the fixes to the owning developer(s) via"
" delegate(...) and wait for the dev subtasks to complete and"
" the cell branch to be re-assembled. Do NOT call submit_up"
" again until new dev work has advanced the cell branch HEAD."
),
context_briefing=briefing,
)
async def submit_root(
self, main_pm_agent_id: UUID, task_id: UUID, notes: str
) -> Envelope:
@@ -0,0 +1,144 @@
"""F007 — the unchanged-PR re-submit loop-stopper is root-only; ``submit_up``
(cell→root) had no head_sha guard, so a weak cell PM could re-submit the
unchanged cell PR and loop ``awaiting_pr_review`` → ``pr_fail`` forever
(the cell-level analogue of the 2026-06-27 root loop F016 closes).
``pr_fail`` stamps the assembled PR's head SHA into
``notes_structured.pr_review.head_sha`` for BOTH cell and root gate tasks
(``pr_gate._capture_pr_head_sha`` / ``_record_gate_verdict`` are
gate-verb-level, not root-level). So the same structural refusal applies
to ``submit_up``: if the cell PR's current head SHA equals the SHA the
last ``pr_fail`` recorded, no new dev work landed on the cell branch ⇒
the diff is byte-identical ⇒ refuse, do not re-open the gate. Every
ambiguous case FAILS OPEN, identical to the root guard (shared
``_current_pr_head_sha``).
"""
from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
import pytest
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
SHA_OLD = "aaaa1111bbbb2222cccc3333dddd4444eeee5555"
SHA_NEW = "9999888877776666555544443333222211110000"
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)
base["journal"].has_decision_for_task.return_value = True
base["journal"].latest_decision_at.return_value = datetime.now(UTC)
base["journal"].has_reflect_for_task.return_value = True
return ChoreographerDeps(**base)
def _resubmit_cell(
*,
notes_structured: dict[str, Any] | None,
pr_number: int | None = 132,
) -> tuple[Choreographer, Any, Any]:
"""A cell-PM task re-submitted from ``in_progress`` after a ``pr_fail``.
Mirrors a live cell re-submit: the cell task is back in ``in_progress``
(re-claimed out of ``needs_revision``), carries the prior ``pr_fail``
verdict in ``notes_structured.pr_review``, and the cell→root PR is still
open. The ``_submit_up_guard`` preflight is satisfied (owned by the cell
PM, journal decision, subtasks terminal, branch present, notes long
enough) so the unchanged-PR gate is the thing under test.
"""
cell_pm_id = uuid4()
cell_task_id = uuid4()
in_prog = MagicMock(
id=cell_task_id,
status="in_progress",
assigned_to=cell_pm_id,
pr_number=pr_number,
branch_name="feature/backend/cell-task",
parent_task_id=uuid4(),
batch_id=None,
team="backend",
notes_structured=notes_structured,
)
gated = MagicMock(**{**in_prog.__dict__, "status": "awaiting_pr_review"})
task_svc = AsyncMock()
task_svc.get.return_value = in_prog
task_svc.submit_for_review.return_value = gated
task_svc.all_subtasks_terminal.return_value = True
task_svc.uncovered_parent_acceptance_criteria.return_value = []
task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
task_svc.session.begin_nested = MagicMock(
return_value=MagicMock(__aenter__=AsyncMock(), __aexit__=AsyncMock())
)
c = Choreographer(_make_deps(task=task_svc, git=AsyncMock()))
cc: Any = c
cc._project_slug_for = AsyncMock(return_value="proj-slug")
return c, cell_pm_id, cell_task_id
@pytest.mark.asyncio
async def test_submit_up_refuses_unchanged_pr_after_pr_fail() -> None:
"""The loop-stopper: prior pr_fail stamped head SHA X, the cell PR head is
still X (no new dev work on the cell branch) → refuse, do not re-open the
gate."""
c, cell_pm_id, cell_task_id = _resubmit_cell(
notes_structured={
"pr_review": {"verdict": "failed", "head_sha": SHA_OLD, "summary": "..."}
}
)
c.git.get_pr_head_sha = AsyncMock(return_value=SHA_OLD)
env = await c.submit_up(
cell_pm_id, cell_task_id, notes="re-submitting the cell after the fix"
)
assert env.error is not None, env.as_dict()
assert env.error == "invalid_state", env.as_dict()
assert "unchanged" in (env.message or "").lower()
remediate = env.remediate or ""
assert "submit_up" in remediate
# The cell PR was NOT re-opened / re-pushed — the runner never ran.
c.task.submit_for_review.assert_not_awaited()
@pytest.mark.asyncio
async def test_submit_up_allows_after_cell_branch_advanced() -> None:
"""A different current head SHA ⇒ dev work landed on the cell branch ⇒ the
diff changed ⇒ allow the re-submit into the gate."""
c, cell_pm_id, cell_task_id = _resubmit_cell(
notes_structured={
"pr_review": {"verdict": "failed", "head_sha": SHA_OLD, "summary": "..."}
}
)
c.git.get_pr_head_sha = AsyncMock(return_value=SHA_NEW)
env = await c.submit_up(
cell_pm_id, cell_task_id, notes="re-submitting after the dev re-assembly"
)
assert env.error is None, env.as_dict()
assert env.status == "awaiting_pr_review"
c.task.submit_for_review.assert_awaited_once()
@pytest.mark.asyncio
async def test_submit_up_fail_open_when_no_prior_pr_fail_verdict() -> None:
"""No pr_review (first submit) ⇒ nothing to compare ⇒ allow."""
c, cell_pm_id, cell_task_id = _resubmit_cell(notes_structured=None)
env = await c.submit_up(
cell_pm_id, cell_task_id, notes="first cell submit; nothing to compare yet"
)
assert env.error is None, env.as_dict()
assert env.status == "awaiting_pr_review"