mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* feat(tasks): task-content guardrails — structured plans + constraints split Bound task PLANNING content the way journals/notes already are, fixing the poor task quality flagged 2026-07-07 (degenerate roots, over-decomposed leaves, descriptions bloated by an auto-attached conventions dump). Phase A — plan/AC guardrails (no migration): - _pm_sub_tasks_gate: cap sub_tasks at 7; per-subtask ceilings (title <=200, description <=600) enforced at both the Pydantic boundary and the gate. Dropped the min-2-roots and no-subtasks-on-code rules: both contradict the 2026-05-08 rule (test_cell_pm_can_plan_code_typed_parent_via_i_will_plan) and break legitimate single-cell roots. Long comment in the gate explains. - IWillPlanRequest: plan <=2000, approach <=800 (floor 150 kept), typed SubTaskCreate/RiskCreate/OpenQuestionCreate replacing loose list[dict]. - DelegateRequest + task_completeness: acceptance_criteria capped at 7 items, each <=200 chars. New FieldRule.MAX_LENGTH_LIST + _post_rule_reject helper (extracted to keep the gate under xenon B). - Routes dump typed models to dicts for the existing rich_plan shaper. Phase B — conventions split (migration 068): - New nullable tasks.constraints Text column; _attach_baseline_constraints now writes the ## Constraints block there instead of appending to description, so description is the human-authored instruction only. The conventions still reach the agent independently at spawn via the ambient block, so agent correctness is unaffected. - TaskResponse / Task model / panel Task type carry constraints; panel shows a read-only Constraints card. Field is optional on the TS type (backend returns null for flag-off / pre-migration rows). Tests: 5 new gate unit tests, 7 schema tests, 3 AC policy tests, 3 e2e smoke scenarios; 4 baseline-constraints integration tests updated. ruff/mypy/xenon clean; 10026 unit+foundation+e2e green; panel typecheck clean. Refs: plan breezy-imagining-kahn * test(tasks): use typed SubTaskCreate instead of dict literals in plan tests make quality runs mypy over tests/ (1079 files), not just roboco/ — the four sites passing dict literals to the now-typed sub_tasks: list[SubTaskCreate] field failed mypy. Construct SubTaskCreate directly; the typed model raising ValidationError IS the boundary the rejection tests assert. * fix(deps): drop unused python-jose — clears PYSEC-2026-1325 (ecdsa, no fix) CI's pip-audit went red on a freshly-published advisory PYSEC-2026-1325 against ecdsa 0.19.2 (no fix published — 0.19.2 is the latest). ecdsa is a transitive dep of python-jose, which is a DIRECT dep of roboco but is NOT imported anywhere in roboco/ or tests/ (grep-verified). The actual JWT path uses PyJWT (import jwt) + fastapi_users.jwt, not python-jose. So python-jose is a dead dependency. Removing it (deletion over an --ignore-vuln waiver) drops ecdsa + rsa + pyasn1 + their type stubs from the lockfile, eliminating the CVE at the source. deptry roboco/ stays clean (no missing-dep), mypy clean, auth + schema tests pass. Master CI was green 9h before this PR's run, so the advisory published in that window would red any run including master — this fix unblocks both. * chore(prompts): regenerate verb tables for typed plan sub_tasks Phase A's IWillPlanRequest schema change (sub_tasks/risks/open_questions from loose list[dict] to typed SubTaskCreate/RiskCreate/OpenQuestionCreate) made the auto-generated verb tables stale. Regenerated via scripts/regenerate_verb_tables.py — the diff is purely the signature reflection (list[str|str] -> list[SubTaskCreate], etc.). Required by the foundation-check gate (Makefile:559). --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
186 lines
6.6 KiB
Python
186 lines
6.6 KiB
Python
"""Tier 1 — task-completeness rules."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
from typing import Any
|
|
|
|
from roboco.foundation.policy import task_completeness as tc
|
|
|
|
MIN_HINT_LEN = 20
|
|
PARENT_PRIORITY_HIGH = 4 # parent task priority used for inheritance assertions
|
|
DEFAULT_PRIORITY_MEDIUM = 2 # fill_priority_from_parent default when no parent
|
|
|
|
|
|
def _task(**fields: Any) -> SimpleNamespace:
|
|
"""Build a SimpleNamespace mimicking a Task with the given fields."""
|
|
defaults = {
|
|
"title": "ok",
|
|
"description": "x" * 30,
|
|
"acceptance_criteria": ["criterion one"],
|
|
"task_type": "code",
|
|
"nature": "technical",
|
|
"estimated_complexity": "medium",
|
|
"team": "backend",
|
|
}
|
|
defaults.update(fields)
|
|
return SimpleNamespace(**defaults)
|
|
|
|
|
|
def test_task_at_create_passes_for_complete_task() -> None:
|
|
result = tc.check(tc.TASK_AT_CREATE, _task())
|
|
assert result.passed is True
|
|
assert result.missing == []
|
|
|
|
|
|
def test_task_at_create_rejects_empty_acceptance_criteria() -> None:
|
|
result = tc.check(tc.TASK_AT_CREATE, _task(acceptance_criteria=[]))
|
|
assert result.passed is False
|
|
assert "acceptance_criteria" in result.missing
|
|
|
|
|
|
def test_task_at_create_rejects_short_description() -> None:
|
|
result = tc.check(tc.TASK_AT_CREATE, _task(description="too short"))
|
|
assert result.passed is False
|
|
assert "description" in result.missing
|
|
|
|
|
|
def test_task_at_create_rejects_missing_nature() -> None:
|
|
result = tc.check(tc.TASK_AT_CREATE, _task(nature=None))
|
|
assert result.passed is False
|
|
assert "nature" in result.missing
|
|
|
|
|
|
def test_denylist_rejects_silent_fallback_phrase() -> None:
|
|
"""Specifically catch the deleted task.py:5061 placeholder."""
|
|
bad = _task(acceptance_criteria=["completed and reviewed by assignee"])
|
|
result = tc.check(tc.TASK_AT_CREATE, bad)
|
|
assert result.passed is False
|
|
assert "acceptance_criteria" in result.missing
|
|
assert any("placeholder" in h.lower() for h in result.field_hints.values())
|
|
|
|
|
|
def test_denylist_rejects_see_title_description() -> None:
|
|
result = tc.check(tc.TASK_AT_CREATE, _task(description="see title"))
|
|
assert result.passed is False
|
|
assert "description" in result.missing
|
|
|
|
|
|
def test_denylist_rejects_todo_description() -> None:
|
|
result = tc.check(tc.TASK_AT_CREATE, _task(description="TODO"))
|
|
assert result.passed is False
|
|
|
|
|
|
def test_completeness_error_carries_missing_and_hints() -> None:
|
|
err = tc.TaskCompletenessError(
|
|
missing=["acceptance_criteria"],
|
|
field_hints={"acceptance_criteria": "non-empty list"},
|
|
)
|
|
assert err.missing == ["acceptance_criteria"]
|
|
assert err.field_hints["acceptance_criteria"] == "non-empty list"
|
|
|
|
|
|
def test_field_hints_for_missing_fields_are_actionable() -> None:
|
|
"""Each hint must mention the field and what valid input looks like."""
|
|
result = tc.check(
|
|
tc.TASK_AT_CREATE,
|
|
_task(
|
|
description="",
|
|
acceptance_criteria=[],
|
|
nature=None,
|
|
),
|
|
)
|
|
for field in ("description", "acceptance_criteria", "nature"):
|
|
assert field in result.field_hints, f"no hint for {field}"
|
|
hint = result.field_hints[field]
|
|
assert len(hint) >= MIN_HINT_LEN, (
|
|
f"hint for {field} too short to be useful: {hint!r}"
|
|
)
|
|
|
|
|
|
def test_fill_team_from_assignee_resolves_dev_slug() -> None:
|
|
payload = {"assigned_to": "be-dev-1"}
|
|
result = tc.fill_team_from_assignee(payload)
|
|
assert result["team"] == "backend"
|
|
assert result["assigned_to"] == "be-dev-1"
|
|
|
|
|
|
def test_fill_team_from_assignee_does_not_overwrite_explicit_team() -> None:
|
|
payload = {"assigned_to": "be-dev-1", "team": "frontend"}
|
|
result = tc.fill_team_from_assignee(payload)
|
|
# Auto-fill never silently overwrites; team stays as caller passed it.
|
|
assert result["team"] == "frontend"
|
|
|
|
|
|
def test_fill_team_from_assignee_unknown_slug_returns_unchanged() -> None:
|
|
payload = {"assigned_to": "notreal-1"}
|
|
result = tc.fill_team_from_assignee(payload)
|
|
# Auto-fill is best-effort; unknown slug = no fill, downstream rejects.
|
|
assert "team" not in result
|
|
|
|
|
|
def test_fill_priority_from_parent_inherits() -> None:
|
|
payload: dict[str, Any] = {}
|
|
parent = SimpleNamespace(priority=PARENT_PRIORITY_HIGH)
|
|
result = tc.fill_priority_from_parent(payload, parent)
|
|
assert result["priority"] == PARENT_PRIORITY_HIGH
|
|
assert result["__priority_inherited"] is True
|
|
|
|
|
|
def test_fill_priority_from_parent_does_not_overwrite_explicit() -> None:
|
|
payload = {"priority": 1}
|
|
parent = SimpleNamespace(priority=PARENT_PRIORITY_HIGH)
|
|
result = tc.fill_priority_from_parent(payload, parent)
|
|
assert result["priority"] == 1
|
|
assert "__priority_inherited" not in result
|
|
|
|
|
|
def test_fill_priority_from_parent_no_parent_uses_medium_default() -> None:
|
|
payload: dict[str, Any] = {}
|
|
result = tc.fill_priority_from_parent(payload, None)
|
|
assert result["priority"] == DEFAULT_PRIORITY_MEDIUM
|
|
assert result["__priority_inherited"] is True
|
|
|
|
|
|
def test_fill_parent_from_active_task_sets_id() -> None:
|
|
payload: dict[str, Any] = {}
|
|
result = tc.fill_parent_from_active_task(payload, "task-id-123")
|
|
assert result["parent_task_id"] == "task-id-123"
|
|
|
|
|
|
def test_fill_parent_from_active_task_does_not_overwrite_explicit() -> None:
|
|
payload = {"parent_task_id": "explicit-id"}
|
|
result = tc.fill_parent_from_active_task(payload, "active-id")
|
|
assert result["parent_task_id"] == "explicit-id"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# AC discipline (2026-07-07 task-quality defect): per-item cap + max count.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_task_at_create_rejects_too_many_acceptance_criteria() -> None:
|
|
"""An AC list >7 items is over-decomposition of criteria."""
|
|
result = tc.check(
|
|
tc.TASK_AT_CREATE, _task(acceptance_criteria=[f"c{i}" for i in range(8)])
|
|
)
|
|
assert result.passed is False
|
|
assert "acceptance_criteria" in result.missing
|
|
|
|
|
|
def test_task_at_create_accepts_seven_acceptance_criteria() -> None:
|
|
"""Exactly 7 AC items is the cap — must pass."""
|
|
result = tc.check(
|
|
tc.TASK_AT_CREATE, _task(acceptance_criteria=[f"c{i}" for i in range(7)])
|
|
)
|
|
assert result.passed is True
|
|
|
|
|
|
def test_task_at_create_rejects_overlong_acceptance_criterion() -> None:
|
|
"""An AC item >200 chars is a restated description, not a criterion."""
|
|
long_ac = "x" * 201
|
|
result = tc.check(tc.TASK_AT_CREATE, _task(acceptance_criteria=[long_ac]))
|
|
assert result.passed is False
|
|
assert "acceptance_criteria" in result.missing
|
|
assert any("200" in h for h in result.field_hints.values())
|