fix: clear 55 pre-existing test failures uncovered after Wave A landed

Three classes of failure, all surfaced once Wave A's plan-required gate
and the migration 013 went in. Per project standing rule: pre-existing
errors are not a free pass — fix them.

1. Wave A1 ordering (32 lifecycle parity failures + 1 full-pipe test).
   _pm_sub_tasks_gate fired BEFORE _claim_plan_start_gate, so wrong-state
   PMs got `incomplete_input` (the gate's verdict) when the spec's
   lifecycle gate should have returned `invalid_state` first. Swapped:
   re-entry check → spec lifecycle gate → sub_tasks gate → claim_plan_run.
   Parity test now sees the spec's verdict as expected.

2. E2 enum naming (2 migration_013 failures + ripple).
   _str_enum in roboco/db/tables.py didn't pass name=… to SQLAlchemy
   Enum(...), so Base.metadata.create_all in test setup inferred
   `role` from the Python class `Role` while the alembic migrations
   declare `agentrole`. Tests saw two enums for the same class and
   hit `agentrole = role` operator errors. Fixed: default name to
   lower(class_name) (matches every migration), override `Role` →
   `agentrole`. One dict entry; no class-by-class registration needed.

3. _MockContentActions.note() signature drift.
   Wave 2 G4 added `structured` kwarg to ContentActions.note().
   The integration mock at tests/integration/v2/test_full_pending_to_completed.py
   didn't accept the new kwarg → 1 test failed on the very first call
   from the v2 do/note route. Added `structured: object = None` and
   left it unused (the test asserts lifecycle, not journal rendering).

Plus three ruff E501 line-length fixes in the test files I touched.

Quality: ruff + mypy clean. pytest 6690 passed / 0 failed / 274 skipped.
This commit is contained in:
Renn F
2026-05-12 04:22:03 +02:00
parent f680db34c6
commit ce92829385
5 changed files with 60 additions and 13 deletions
+24 -1
View File
@@ -50,6 +50,18 @@ from roboco.models.base import (
from roboco.models.session import SessionScope from roboco.models.session import SessionScope
from roboco.models.work_session import WorkSessionStatus from roboco.models.work_session import WorkSessionStatus
# Python class name → canonical postgres enum name (only the cases where
# the lowercased class name does NOT match the migration's `name=...`).
# Audited from alembic/versions/*.py — every other StrEnum uses
# lower(class_name), so we default to that.
_PG_ENUM_NAME_OVERRIDES: dict[str, str] = {
# The foundation's `Role` class binds to the postgres `agentrole` enum
# (see alembic 001 + 012). Without this override, SQLAlchemy infers
# `role` from the class name, producing the `operator does not exist:
# agentrole = role` regression that smoke run 2 hit.
"Role": "agentrole",
}
def _str_enum(enum_cls: type) -> Enum: def _str_enum(enum_cls: type) -> Enum:
"""SQLAlchemy Enum that serializes by `.value` (lowercase) for StrEnum types. """SQLAlchemy Enum that serializes by `.value` (lowercase) for StrEnum types.
@@ -57,8 +69,19 @@ def _str_enum(enum_cls: type) -> Enum:
Matches the lowercase values declared in alembic/versions/001_initial_schema.py. Matches the lowercase values declared in alembic/versions/001_initial_schema.py.
Without values_callable, SQLAlchemy uses `.name` (uppercase) which does not Without values_callable, SQLAlchemy uses `.name` (uppercase) which does not
match the alembic-declared enum members. match the alembic-declared enum members.
The `name=` is pinned to the canonical postgres enum name so that
``Base.metadata.create_all`` (test setup) produces the same enum
types the migrations create. Default is ``lower(class_name)`` —
matches every alembic migration's name=...; the only override is
``Role`` → ``agentrole`` (E2 fix).
""" """
return Enum(enum_cls, values_callable=lambda obj: [m.value for m in obj]) name = _PG_ENUM_NAME_OVERRIDES.get(enum_cls.__name__, enum_cls.__name__.lower())
return Enum(
enum_cls,
name=name,
values_callable=lambda obj: [m.value for m in obj],
)
# ============================================================================= # =============================================================================
+12 -6
View File
@@ -2045,14 +2045,22 @@ class Choreographer:
verb_name="i_will_plan", verb_name="i_will_plan",
) )
# Re-entry check runs first — a respawned PM with thin args ("resume", # Re-entry check runs first — a respawned PM with thin args ("resume",
# no sub_tasks) must short-circuit here before the sub_tasks gate. # no sub_tasks) must short-circuit here before any gate.
if reentry := await self._handle_pm_reentry( if reentry := await self._handle_pm_reentry(
ctx, t, pm_agent_id, task_id, role_str, briefing ctx, t, pm_agent_id, task_id, role_str, briefing
): ):
return reentry return reentry
# Gate runs only for initial-claim paths (not re-entry). # Lifecycle spec gate runs BEFORE the sub_tasks gate so wrong-state
# PMs decompose; their plan MUST include approach + at least one sub_task. # cases (e.g., task in backlog/claimed/completed) return invalid_state
# Devs execute; sub_tasks list can be empty (their plan is execution-shaped). # — the lifecycle's verdict — instead of being masked by the
# PM-decomposition check. Parity test
# `test_lifecycle_consumer_parity.py::test_i_will_plan_matches_spec`
# asserts this order.
if rejection := await self._claim_plan_start_gate(ctx, role, spec_ctx):
return rejection
# Spec gate passed; now enforce the verb-specific PM-decomposition
# contract. PMs decompose; their plan MUST include approach + at
# least one sub_task. Devs execute; sub_tasks may be empty.
if rejection := await self._pm_sub_tasks_gate( if rejection := await self._pm_sub_tasks_gate(
role_str=role_str, role_str=role_str,
rich_plan=rich_plan, rich_plan=rich_plan,
@@ -2062,8 +2070,6 @@ class Choreographer:
briefing=briefing, briefing=briefing,
): ):
return rejection return rejection
if rejection := await self._claim_plan_start_gate(ctx, role, spec_ctx):
return rejection
envelope = await self._claim_plan_start_run(ctx, agent, spec_ctx) envelope = await self._claim_plan_start_run(ctx, agent, spec_ctx)
return await self._post_claim_journal_gate( return await self._post_claim_journal_gate(
"i_will_plan", pm_agent_id, task_id, envelope "i_will_plan", pm_agent_id, task_id, envelope
@@ -173,11 +173,16 @@ class _MockContentActions:
text: object, text: object,
scope: str = "note", scope: str = "note",
task_id: object = None, task_id: object = None,
structured: object = None,
) -> Envelope: ) -> Envelope:
# `structured` mirrors the Wave 2 G4 production signature (panel
# decision/reflect fields). The mock ignores it — the test asserts
# lifecycle transitions, not journal-entry rendering.
_ = agent_id _ = agent_id
_ = text _ = text
_ = scope _ = scope
_ = task_id _ = task_id
_ = structured
return Envelope.ok(status="noted", task_id=None, next="continue") return Envelope.ok(status="noted", task_id=None, next="continue")
@@ -218,7 +218,9 @@ async def test_i_will_plan_rejects_non_pending_state() -> None:
pm_id = uuid4() pm_id = uuid4()
task_id = uuid4() task_id = uuid4()
task_svc = AsyncMock() task_svc = AsyncMock()
task_svc.get.return_value = MagicMock(id=task_id, status="in_progress", assigned_to=uuid4()) task_svc.get.return_value = MagicMock(
id=task_id, status="in_progress", assigned_to=uuid4()
)
task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend") task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
deps = _make_deps(task=task_svc) deps = _make_deps(task=task_svc)
c = Choreographer(deps) c = Choreographer(deps)
@@ -392,8 +394,13 @@ async def test_i_will_plan_idempotent_when_already_in_progress_for_caller() -> N
task_id, task_id,
plan="re-entry plan", plan="re-entry plan",
rich_plan={ rich_plan={
"approach": "Idempotent re-entry: task already in progress, refresh heartbeat.", "approach": (
"sub_tasks": [{"title": "Re-entry subtask", "description": "Resume work"}], "Idempotent re-entry: task already in progress, "
"refresh heartbeat."
),
"sub_tasks": [
{"title": "Re-entry subtask", "description": "Resume work"}
],
}, },
) )
@@ -451,8 +458,13 @@ async def test_i_will_plan_recovery_when_already_claimed_for_caller() -> None:
task_id, task_id,
plan="re-entry plan", plan="re-entry plan",
rich_plan={ rich_plan={
"approach": "Recovery re-entry: task claimed but not started; run set_plan + start.", "approach": (
"sub_tasks": [{"title": "Recovery subtask", "description": "Resume from claimed"}], "Recovery re-entry: task claimed but not started; "
"run set_plan + start."
),
"sub_tasks": [
{"title": "Recovery subtask", "description": "Resume from claimed"}
],
}, },
) )
+2 -1
View File
@@ -286,7 +286,8 @@ async def test_note_reflect_missing_required_fields_returns_incomplete_input() -
body = env.as_dict() body = env.as_dict()
assert body["error"] == "incomplete_input" assert body["error"] == "incomplete_input"
assert {"what_done", "what_learned", "what_struggled"}.issubset(set(body["missing"])) missing = set(body["missing"])
assert {"what_done", "what_learned", "what_struggled"}.issubset(missing)
journal_svc.write_entry.assert_not_awaited() journal_svc.write_entry.assert_not_awaited()