2026-05-02 03:11:49 +02:00
|
|
|
"""Tests for evidence-payload + context-briefing assembly."""
|
|
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
2026-06-10 12:04:24 +02:00
|
|
|
from typing import Any
|
2026-05-02 03:11:49 +02:00
|
|
|
from unittest.mock import MagicMock
|
|
|
|
|
from uuid import uuid4
|
|
|
|
|
|
|
|
|
|
from roboco.services.gateway.evidence_builder import (
|
|
|
|
|
BRIEFING_LIST_CAP,
|
|
|
|
|
BriefingInputs,
|
|
|
|
|
build_context_briefing,
|
|
|
|
|
build_evidence_for_task,
|
2026-06-10 12:04:24 +02:00
|
|
|
build_task_handoff,
|
2026-05-02 03:11:49 +02:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _task(
|
|
|
|
|
*,
|
|
|
|
|
pr_number: int | None = 8,
|
|
|
|
|
pr_url: str | None = "https://github.com/x/y/pull/8",
|
|
|
|
|
commits: list[dict] | None = None,
|
|
|
|
|
dev_notes: str = "did stuff",
|
|
|
|
|
) -> MagicMock:
|
|
|
|
|
t = MagicMock()
|
|
|
|
|
t.id = uuid4()
|
|
|
|
|
t.pr_number = pr_number
|
|
|
|
|
t.pr_url = pr_url
|
|
|
|
|
t.commits = commits or [{"sha": "abc123", "message": "feat: x"}]
|
|
|
|
|
t.dev_notes = dev_notes
|
|
|
|
|
t.acceptance_criteria_status = []
|
|
|
|
|
return t
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestEvidence:
|
|
|
|
|
def test_basic_payload(self) -> None:
|
|
|
|
|
t = _task()
|
|
|
|
|
ev = build_evidence_for_task(
|
|
|
|
|
t, journal_highlights=[], files_changed=["README.md"]
|
|
|
|
|
)
|
|
|
|
|
assert ev.pr_url == "https://github.com/x/y/pull/8"
|
|
|
|
|
assert ev.commits == [{"sha": "abc123", "message": "feat: x"}]
|
|
|
|
|
assert "README.md" in ev.files_changed
|
|
|
|
|
|
|
|
|
|
def test_no_pr_returns_empty_url(self) -> None:
|
|
|
|
|
t = _task(pr_number=None, pr_url=None)
|
|
|
|
|
ev = build_evidence_for_task(t, journal_highlights=[], files_changed=[])
|
|
|
|
|
assert ev.pr_url is None
|
|
|
|
|
assert ev.pr_number is None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestContextBriefing:
|
|
|
|
|
def test_empty_briefing(self) -> None:
|
|
|
|
|
inputs = BriefingInputs(
|
|
|
|
|
unread_a2a=[],
|
|
|
|
|
unread_mentions=[],
|
|
|
|
|
pending_notifications=[],
|
|
|
|
|
task_metadata_gaps=[],
|
|
|
|
|
recent_team_activity=[],
|
|
|
|
|
blockers_in_my_lane=[],
|
|
|
|
|
)
|
|
|
|
|
b = build_context_briefing(inputs)
|
|
|
|
|
for key in (
|
|
|
|
|
"unread_a2a",
|
|
|
|
|
"unread_mentions",
|
|
|
|
|
"pending_notifications",
|
|
|
|
|
"task_metadata_gaps",
|
|
|
|
|
"recent_team_activity",
|
|
|
|
|
"blockers_in_my_lane",
|
|
|
|
|
):
|
|
|
|
|
assert b[key] == []
|
|
|
|
|
|
|
|
|
|
def test_lists_capped_at_10(self) -> None:
|
|
|
|
|
twenty = [{"i": i} for i in range(20)]
|
|
|
|
|
inputs = BriefingInputs(
|
|
|
|
|
unread_a2a=twenty,
|
|
|
|
|
unread_mentions=twenty,
|
|
|
|
|
pending_notifications=twenty,
|
|
|
|
|
task_metadata_gaps=[],
|
|
|
|
|
recent_team_activity=twenty,
|
|
|
|
|
blockers_in_my_lane=twenty,
|
|
|
|
|
)
|
|
|
|
|
b = build_context_briefing(inputs)
|
|
|
|
|
assert len(b["unread_a2a"]) == BRIEFING_LIST_CAP
|
|
|
|
|
assert len(b["unread_mentions"]) == BRIEFING_LIST_CAP
|
|
|
|
|
assert len(b["pending_notifications"]) == BRIEFING_LIST_CAP
|
|
|
|
|
assert len(b["recent_team_activity"]) == BRIEFING_LIST_CAP
|
|
|
|
|
assert len(b["blockers_in_my_lane"]) == BRIEFING_LIST_CAP
|
2026-06-10 12:04:24 +02:00
|
|
|
|
|
|
|
|
def test_task_handoff_defaults_none_and_surfaces_in_briefing(self) -> None:
|
|
|
|
|
inputs = BriefingInputs(
|
|
|
|
|
unread_a2a=[],
|
|
|
|
|
unread_mentions=[],
|
|
|
|
|
pending_notifications=[],
|
|
|
|
|
task_metadata_gaps=[],
|
|
|
|
|
recent_team_activity=[],
|
|
|
|
|
blockers_in_my_lane=[],
|
|
|
|
|
)
|
|
|
|
|
assert build_context_briefing(inputs)["task_handoff"] is None
|
|
|
|
|
|
|
|
|
|
with_handoff = BriefingInputs(
|
|
|
|
|
unread_a2a=[],
|
|
|
|
|
unread_mentions=[],
|
|
|
|
|
pending_notifications=[],
|
|
|
|
|
task_metadata_gaps=[],
|
|
|
|
|
recent_team_activity=[],
|
|
|
|
|
blockers_in_my_lane=[],
|
|
|
|
|
task_handoff={"pr_number": 8},
|
|
|
|
|
)
|
|
|
|
|
assert build_context_briefing(with_handoff)["task_handoff"] == {"pr_number": 8}
|
|
|
|
|
|
2026-06-15 20:47:41 +02:00
|
|
|
def test_company_goals_defaults_none_and_surfaces_in_briefing(self) -> None:
|
|
|
|
|
inputs = BriefingInputs(
|
|
|
|
|
unread_a2a=[],
|
|
|
|
|
unread_mentions=[],
|
|
|
|
|
pending_notifications=[],
|
|
|
|
|
task_metadata_gaps=[],
|
|
|
|
|
recent_team_activity=[],
|
|
|
|
|
blockers_in_my_lane=[],
|
|
|
|
|
)
|
|
|
|
|
assert build_context_briefing(inputs)["company_goals"] is None
|
|
|
|
|
|
|
|
|
|
with_goals = BriefingInputs(
|
|
|
|
|
unread_a2a=[],
|
|
|
|
|
unread_mentions=[],
|
|
|
|
|
pending_notifications=[],
|
|
|
|
|
task_metadata_gaps=[],
|
|
|
|
|
recent_team_activity=[],
|
|
|
|
|
blockers_in_my_lane=[],
|
|
|
|
|
company_goals={"north_star": "win"},
|
|
|
|
|
)
|
|
|
|
|
assert build_context_briefing(with_goals)["company_goals"] == {
|
|
|
|
|
"north_star": "win"
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-10 12:04:24 +02:00
|
|
|
|
|
|
|
|
class TestTaskHandoff:
|
|
|
|
|
def test_none_task_returns_none(self) -> None:
|
|
|
|
|
assert build_task_handoff(None, []) is None
|
|
|
|
|
|
|
|
|
|
def test_no_prior_work_returns_none(self) -> None:
|
|
|
|
|
t = _task(pr_number=None, pr_url=None, dev_notes="")
|
|
|
|
|
t.commits = [] # _task's `commits or [...]` default would re-seed one
|
|
|
|
|
t.acceptance_criteria_status = []
|
|
|
|
|
assert build_task_handoff(t, []) is None
|
|
|
|
|
|
|
|
|
|
def test_digest_from_prior_work(self) -> None:
|
|
|
|
|
pr = 8
|
|
|
|
|
t = _task(
|
|
|
|
|
pr_number=pr,
|
|
|
|
|
commits=[{"sha": "abc", "message": "feat: x"}],
|
|
|
|
|
dev_notes="implemented the parser",
|
|
|
|
|
)
|
|
|
|
|
t.branch_name = "feature/backend/abc"
|
|
|
|
|
t.acceptance_criteria_status = [{"criterion": "parses", "met": True}]
|
|
|
|
|
digest = build_task_handoff(t, [{"summary": "chose recursive descent"}])
|
|
|
|
|
assert digest is not None
|
|
|
|
|
assert digest["pr_number"] == pr
|
|
|
|
|
assert digest["branch_name"] == "feature/backend/abc"
|
|
|
|
|
assert digest["commit_count"] == 1
|
|
|
|
|
assert digest["dev_summary"] == "implemented the parser"
|
|
|
|
|
assert digest["journal_highlights"] == [{"summary": "chose recursive descent"}]
|
|
|
|
|
|
|
|
|
|
def test_surfaces_completed_dependencies(self) -> None:
|
|
|
|
|
dep_id = uuid4()
|
|
|
|
|
t = _task(pr_number=None, pr_url=None, dev_notes="")
|
|
|
|
|
t.commits = []
|
|
|
|
|
t.acceptance_criteria_status = []
|
|
|
|
|
t.completed_dependency_ids = [dep_id]
|
|
|
|
|
digest = build_task_handoff(t, [])
|
|
|
|
|
# A just-unblocked task with no other prior work still surfaces the dep.
|
|
|
|
|
assert digest is not None
|
|
|
|
|
assert digest["completed_dependency_ids"] == [str(dep_id)]
|
|
|
|
|
|
|
|
|
|
def test_caps_lists_and_type_guards(self) -> None:
|
|
|
|
|
thirty = [{"sha": str(i)} for i in range(30)]
|
|
|
|
|
t = _task(pr_number=7, commits=thirty)
|
|
|
|
|
# Non-list / mismatched-type attributes degrade safely, never leak.
|
|
|
|
|
t.acceptance_criteria_status = object()
|
|
|
|
|
t.pr_url = object()
|
|
|
|
|
t.branch_name = None
|
|
|
|
|
not_a_list: Any = object()
|
|
|
|
|
digest = build_task_handoff(t, not_a_list)
|
|
|
|
|
assert digest is not None
|
|
|
|
|
assert len(digest["recent_commits"]) == BRIEFING_LIST_CAP
|
|
|
|
|
assert digest["acceptance_criteria_status"] == []
|
|
|
|
|
assert digest["journal_highlights"] == []
|
|
|
|
|
assert digest["pr_url"] is None
|
|
|
|
|
assert digest["branch_name"] is None
|
2026-06-28 10:25:53 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestPrReviewSurface:
|
|
|
|
|
"""F008 — the persisted pr_fail verdict + issues must surface in the PM
|
|
|
|
|
briefing's task_handoff, not just the fire-and-forget a2a. A PM respawned
|
|
|
|
|
into ``needs_revision`` after a pr_fail otherwise sees a generic "needs
|
|
|
|
|
revision" with zero concrete change-requests and re-submits the same PR."""
|
|
|
|
|
|
|
|
|
|
def test_surfaces_pr_fail_verdict_and_issues(self) -> None:
|
|
|
|
|
t = _task(pr_number=138, commits=[{"sha": "abc", "message": "feat: x"}])
|
|
|
|
|
t.notes_structured = {
|
|
|
|
|
"pr_review": {
|
|
|
|
|
"verdict": "failed",
|
|
|
|
|
"summary": "In-path PR-review gate requested changes.",
|
|
|
|
|
"issues": ["missing null guard", "no test for the edge case"],
|
|
|
|
|
"head_sha": "aaaa1111bbbb2222",
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
digest = build_task_handoff(t, [])
|
|
|
|
|
assert digest is not None
|
|
|
|
|
pr_review = digest["pr_review"]
|
|
|
|
|
assert pr_review["verdict"] == "failed"
|
|
|
|
|
assert pr_review["issues"] == [
|
|
|
|
|
"missing null guard",
|
|
|
|
|
"no test for the edge case",
|
|
|
|
|
]
|
|
|
|
|
assert pr_review["head_sha"] == "aaaa1111bbbb2222"
|
|
|
|
|
|
|
|
|
|
def test_no_pr_review_field_when_none_present(self) -> None:
|
|
|
|
|
t = _task(pr_number=8, commits=[{"sha": "abc", "message": "feat: x"}])
|
|
|
|
|
t.notes_structured = None
|
|
|
|
|
digest = build_task_handoff(t, [])
|
|
|
|
|
assert digest is not None
|
|
|
|
|
# Absent pr_review ⇒ no key (not a None-valued key) so a PM without a
|
|
|
|
|
# prior gate verdict doesn't see a misleading empty slot.
|
|
|
|
|
assert "pr_review" not in digest
|
|
|
|
|
|
|
|
|
|
def test_pr_review_alone_is_prior_work_worth_resuming(self) -> None:
|
|
|
|
|
"""A task with no commits/dev-notes but a prior pr_fail verdict still
|
|
|
|
|
surfaces the handoff so the owning PM reads the change-requests."""
|
|
|
|
|
t = _task(pr_number=None, pr_url=None, dev_notes="")
|
|
|
|
|
t.commits = []
|
|
|
|
|
t.acceptance_criteria_status = []
|
|
|
|
|
t.notes_structured = {
|
|
|
|
|
"pr_review": {"verdict": "failed", "issues": ["fix the off-by-one"]}
|
|
|
|
|
}
|
|
|
|
|
digest = build_task_handoff(t, [])
|
|
|
|
|
assert digest is not None
|
|
|
|
|
assert digest["pr_review"]["issues"] == ["fix the off-by-one"]
|