Files
Timmy-time-dashboard/tests/dashboard/test_scorecards.py
Kimi Agent fe7e14b10e
Some checks failed
Tests / lint (push) Successful in 23s
Tests / test (push) Has been cancelled
[kimi] Split scorecard_service.py into focused modules (#1406) (#1461)
2026-03-24 20:06:31 +00:00

676 lines
25 KiB
Python

"""Tests for agent scorecard functionality."""
from datetime import UTC, datetime, timedelta
from unittest.mock import MagicMock, patch
from dashboard.services.scorecard import (
AgentMetrics,
PeriodType,
ScorecardSummary,
generate_all_scorecards,
generate_scorecard,
get_tracked_agents,
)
from dashboard.services.scorecard.aggregators import aggregate_metrics, query_token_transactions
from dashboard.services.scorecard.calculators import detect_patterns
from dashboard.services.scorecard.formatters import generate_narrative_bullets
from dashboard.services.scorecard.validators import (
extract_actor_from_event,
get_period_bounds,
is_tracked_agent,
)
from infrastructure.events.bus import Event
class TestPeriodBounds:
"""Test period boundary calculations."""
def test_daily_period_bounds(self):
"""Test daily period returns correct 24-hour window."""
reference = datetime(2026, 3, 21, 12, 30, 45, tzinfo=UTC)
start, end = get_period_bounds(PeriodType.daily, reference)
assert end == datetime(2026, 3, 21, 0, 0, 0, tzinfo=UTC)
assert start == datetime(2026, 3, 20, 0, 0, 0, tzinfo=UTC)
assert (end - start) == timedelta(days=1)
def test_weekly_period_bounds(self):
"""Test weekly period returns correct 7-day window."""
reference = datetime(2026, 3, 21, 12, 30, 45, tzinfo=UTC)
start, end = get_period_bounds(PeriodType.weekly, reference)
assert end == datetime(2026, 3, 21, 0, 0, 0, tzinfo=UTC)
assert start == datetime(2026, 3, 14, 0, 0, 0, tzinfo=UTC)
assert (end - start) == timedelta(days=7)
def test_default_reference_date(self):
"""Test default reference date uses current time."""
start, end = get_period_bounds(PeriodType.daily)
now = datetime.now(UTC)
# End should be start of current day (midnight)
expected_end = now.replace(hour=0, minute=0, second=0, microsecond=0)
assert end == expected_end
# Start should be 24 hours before end
assert (end - start) == timedelta(days=1)
class TestTrackedAgents:
"""Test agent tracking functions."""
def test_get_tracked_agents(self):
"""Test get_tracked_agents returns sorted list."""
agents = get_tracked_agents()
assert isinstance(agents, list)
assert "kimi" in agents
assert "claude" in agents
assert "gemini" in agents
assert "hermes" in agents
assert "manus" in agents
assert agents == sorted(agents)
def test_is_tracked_agent_true(self):
"""Test _is_tracked_agent returns True for tracked agents."""
assert is_tracked_agent("kimi") is True
assert is_tracked_agent("KIMI") is True # case insensitive
assert is_tracked_agent("claude") is True
assert is_tracked_agent("hermes") is True
def test_is_tracked_agent_false(self):
"""Test _is_tracked_agent returns False for untracked agents."""
assert is_tracked_agent("unknown") is False
assert is_tracked_agent("rockachopa") is False
assert is_tracked_agent("") is False
class TestExtractActor:
"""Test actor extraction from events."""
def test_extract_from_actor_field(self):
"""Test extraction from data.actor field."""
event = Event(type="test", source="system", data={"actor": "kimi"})
assert extract_actor_from_event(event) == "kimi"
def test_extract_from_agent_id_field(self):
"""Test extraction from data.agent_id field."""
event = Event(type="test", source="system", data={"agent_id": "claude"})
assert extract_actor_from_event(event) == "claude"
def test_extract_from_source_fallback(self):
"""Test fallback to event.source."""
event = Event(type="test", source="gemini", data={})
assert extract_actor_from_event(event) == "gemini"
def test_actor_priority_over_agent_id(self):
"""Test actor field takes priority over agent_id."""
event = Event(type="test", source="system", data={"actor": "kimi", "agent_id": "claude"})
assert extract_actor_from_event(event) == "kimi"
class TestAggregateMetrics:
"""Test metrics aggregation from events."""
def test_empty_events(self):
"""Test aggregation with no events returns empty dict."""
result = aggregate_metrics([])
assert result == {}
def test_push_event_aggregation(self):
"""Test push events aggregate commits correctly."""
events = [
Event(type="gitea.push", source="gitea", data={"actor": "kimi", "num_commits": 3}),
Event(type="gitea.push", source="gitea", data={"actor": "kimi", "num_commits": 2}),
]
result = aggregate_metrics(events)
assert "kimi" in result
assert result["kimi"].commits == 5
def test_issue_opened_aggregation(self):
"""Test issue opened events aggregate correctly."""
events = [
Event(
type="gitea.issue.opened",
source="gitea",
data={"actor": "claude", "issue_number": 100},
),
Event(
type="gitea.issue.opened",
source="gitea",
data={"actor": "claude", "issue_number": 101},
),
]
result = aggregate_metrics(events)
assert "claude" in result
assert len(result["claude"].issues_touched) == 2
assert 100 in result["claude"].issues_touched
assert 101 in result["claude"].issues_touched
def test_comment_aggregation(self):
"""Test comment events aggregate correctly."""
events = [
Event(
type="gitea.issue.comment",
source="gitea",
data={"actor": "gemini", "issue_number": 100},
),
Event(
type="gitea.issue.comment",
source="gitea",
data={"actor": "gemini", "issue_number": 101},
),
]
result = aggregate_metrics(events)
assert "gemini" in result
assert result["gemini"].comments == 2
assert len(result["gemini"].issues_touched) == 2 # Comments touch issues too
def test_pr_events_aggregation(self):
"""Test PR open and merge events aggregate correctly."""
events = [
Event(
type="gitea.pull_request",
source="gitea",
data={"actor": "kimi", "pr_number": 50, "action": "opened"},
),
Event(
type="gitea.pull_request",
source="gitea",
data={"actor": "kimi", "pr_number": 50, "action": "closed", "merged": True},
),
Event(
type="gitea.pull_request",
source="gitea",
data={"actor": "kimi", "pr_number": 51, "action": "opened"},
),
]
result = aggregate_metrics(events)
assert "kimi" in result
assert len(result["kimi"].prs_opened) == 2
assert len(result["kimi"].prs_merged) == 1
assert 50 in result["kimi"].prs_merged
def test_untracked_agent_filtered(self):
"""Test events from untracked agents are filtered out."""
events = [
Event(
type="gitea.push", source="gitea", data={"actor": "rockachopa", "num_commits": 5}
),
]
result = aggregate_metrics(events)
assert "rockachopa" not in result
def test_task_completion_aggregation(self):
"""Test task completion events aggregate test files."""
events = [
Event(
type="agent.task.completed",
source="gitea",
data={
"agent_id": "kimi",
"tests_affected": ["test_foo.py", "test_bar.py"],
"token_reward": 10,
},
),
]
result = aggregate_metrics(events)
assert "kimi" in result
assert len(result["kimi"].tests_affected) == 2
assert "test_foo.py" in result["kimi"].tests_affected
assert result["kimi"].tokens_earned == 10
class TestAgentMetrics:
"""Test AgentMetrics class."""
def test_merge_rate_zero_prs(self):
"""Test merge rate is 0 when no PRs opened."""
metrics = AgentMetrics(agent_id="kimi")
assert metrics.pr_merge_rate == 0.0
def test_merge_rate_perfect(self):
"""Test 100% merge rate calculation."""
metrics = AgentMetrics(agent_id="kimi", prs_opened={1, 2, 3}, prs_merged={1, 2, 3})
assert metrics.pr_merge_rate == 1.0
def test_merge_rate_partial(self):
"""Test partial merge rate calculation."""
metrics = AgentMetrics(agent_id="kimi", prs_opened={1, 2, 3, 4}, prs_merged={1, 2})
assert metrics.pr_merge_rate == 0.5
class TestDetectPatterns:
"""Test pattern detection logic."""
def test_high_merge_rate_pattern(self):
"""Test detection of high merge rate pattern."""
metrics = AgentMetrics(
agent_id="kimi",
prs_opened={1, 2, 3, 4, 5},
prs_merged={1, 2, 3, 4}, # 80% merge rate
)
patterns = detect_patterns(metrics)
assert any("High merge rate" in p for p in patterns)
def test_low_merge_rate_pattern(self):
"""Test detection of low merge rate pattern."""
metrics = AgentMetrics(
agent_id="kimi",
prs_opened={1, 2, 3, 4, 5},
prs_merged={1}, # 20% merge rate
)
patterns = detect_patterns(metrics)
assert any("low merge rate" in p for p in patterns)
def test_high_commits_no_prs_pattern(self):
"""Test detection of direct-to-main commits pattern."""
metrics = AgentMetrics(
agent_id="kimi",
commits=15,
prs_opened=set(),
)
patterns = detect_patterns(metrics)
assert any("High commit volume without PRs" in p for p in patterns)
def test_silent_worker_pattern(self):
"""Test detection of silent worker pattern."""
metrics = AgentMetrics(
agent_id="kimi",
issues_touched={1, 2, 3, 4, 5, 6},
comments=0,
)
patterns = detect_patterns(metrics)
assert any("silent worker" in p for p in patterns)
def test_communicative_pattern(self):
"""Test detection of highly communicative pattern."""
metrics = AgentMetrics(
agent_id="kimi",
issues_touched={1, 2}, # 2 issues
comments=10, # 5x comments per issue
)
patterns = detect_patterns(metrics)
assert any("Highly communicative" in p for p in patterns)
def test_token_accumulation_pattern(self):
"""Test detection of token accumulation pattern."""
metrics = AgentMetrics(
agent_id="kimi",
tokens_earned=150,
tokens_spent=10,
)
patterns = detect_patterns(metrics)
assert any("Strong token accumulation" in p for p in patterns)
def test_token_spend_pattern(self):
"""Test detection of high token spend pattern."""
metrics = AgentMetrics(
agent_id="kimi",
tokens_earned=10,
tokens_spent=100,
)
patterns = detect_patterns(metrics)
assert any("High token spend" in p for p in patterns)
class TestGenerateNarrative:
"""Test narrative bullet generation."""
def test_empty_metrics_narrative(self):
"""Test narrative for empty metrics mentions no activity."""
metrics = AgentMetrics(agent_id="kimi")
bullets = generate_narrative_bullets(metrics, PeriodType.daily)
assert len(bullets) == 1
assert "No recorded activity" in bullets[0]
def test_activity_summary_narrative(self):
"""Test narrative includes activity summary."""
metrics = AgentMetrics(
agent_id="kimi",
commits=5,
prs_opened={1, 2},
prs_merged={1},
)
bullets = generate_narrative_bullets(metrics, PeriodType.daily)
activity_bullet = next((b for b in bullets if "Active across" in b), None)
assert activity_bullet is not None
assert "5 commits" in activity_bullet
assert "2 PRs opened" in activity_bullet
assert "1 PR merged" in activity_bullet
def test_tests_affected_narrative(self):
"""Test narrative includes tests affected."""
metrics = AgentMetrics(
agent_id="kimi",
tests_affected={"test_a.py", "test_b.py"},
)
bullets = generate_narrative_bullets(metrics, PeriodType.daily)
assert any("2 test files" in b for b in bullets)
def test_tokens_earned_narrative(self):
"""Test narrative includes token earnings."""
metrics = AgentMetrics(
agent_id="kimi",
tokens_earned=100,
tokens_spent=20,
)
bullets = generate_narrative_bullets(metrics, PeriodType.daily)
assert any("Net earned 80 tokens" in b for b in bullets)
def test_tokens_spent_narrative(self):
"""Test narrative includes token spending."""
metrics = AgentMetrics(
agent_id="kimi",
tokens_earned=20,
tokens_spent=100,
)
bullets = generate_narrative_bullets(metrics, PeriodType.daily)
assert any("Net spent 80 tokens" in b for b in bullets)
def test_balanced_tokens_narrative(self):
"""Test narrative for balanced token flow."""
metrics = AgentMetrics(
agent_id="kimi",
tokens_earned=100,
tokens_spent=100,
)
bullets = generate_narrative_bullets(metrics, PeriodType.daily)
assert any("Balanced token flow" in b for b in bullets)
class TestScorecardSummary:
"""Test ScorecardSummary dataclass."""
def test_to_dict_structure(self):
"""Test to_dict returns expected structure."""
metrics = AgentMetrics(
agent_id="kimi",
issues_touched={1, 2},
prs_opened={10, 11},
prs_merged={10},
tokens_earned=100,
tokens_spent=20,
)
summary = ScorecardSummary(
agent_id="kimi",
period_type=PeriodType.daily,
period_start=datetime.now(UTC),
period_end=datetime.now(UTC),
metrics=metrics,
narrative_bullets=["Test bullet"],
patterns=["Test pattern"],
)
data = summary.to_dict()
assert data["agent_id"] == "kimi"
assert data["period_type"] == "daily"
assert "metrics" in data
assert data["metrics"]["issues_touched"] == 2
assert data["metrics"]["prs_opened"] == 2
assert data["metrics"]["prs_merged"] == 1
assert data["metrics"]["pr_merge_rate"] == 0.5
assert data["metrics"]["tokens_earned"] == 100
assert data["metrics"]["token_net"] == 80
assert data["narrative_bullets"] == ["Test bullet"]
assert data["patterns"] == ["Test pattern"]
class TestQueryTokenTransactions:
"""Test token transaction querying."""
def test_empty_ledger(self):
"""Test empty ledger returns zero values."""
with patch("lightning.ledger.get_transactions", return_value=[]):
earned, spent = query_token_transactions("kimi", datetime.now(UTC), datetime.now(UTC))
assert earned == 0
assert spent == 0
def test_ledger_with_transactions(self):
"""Test ledger aggregation of transactions."""
now = datetime.now(UTC)
mock_tx = [
MagicMock(
agent_id="kimi",
tx_type=MagicMock(value="incoming"),
amount_sats=100,
created_at=now.isoformat(),
),
MagicMock(
agent_id="kimi",
tx_type=MagicMock(value="outgoing"),
amount_sats=30,
created_at=now.isoformat(),
),
]
with patch("lightning.ledger.get_transactions", return_value=mock_tx):
earned, spent = query_token_transactions(
"kimi", now - timedelta(hours=1), now + timedelta(hours=1)
)
assert earned == 100
assert spent == 30
def test_ledger_filters_by_agent(self):
"""Test ledger filters transactions by agent_id."""
now = datetime.now(UTC)
mock_tx = [
MagicMock(
agent_id="claude",
tx_type=MagicMock(value="incoming"),
amount_sats=100,
created_at=now.isoformat(),
),
]
with patch("lightning.ledger.get_transactions", return_value=mock_tx):
earned, spent = query_token_transactions(
"kimi", now - timedelta(hours=1), now + timedelta(hours=1)
)
assert earned == 0 # Transaction was for claude, not kimi
def test_ledger_filters_by_time(self):
"""Test ledger filters transactions by time range."""
now = datetime.now(UTC)
old_time = now - timedelta(days=2)
mock_tx = [
MagicMock(
agent_id="kimi",
tx_type=MagicMock(value="incoming"),
amount_sats=100,
created_at=old_time.isoformat(),
),
]
with patch("lightning.ledger.get_transactions", return_value=mock_tx):
# Query for today only
earned, spent = query_token_transactions(
"kimi", now - timedelta(hours=1), now + timedelta(hours=1)
)
assert earned == 0 # Transaction was 2 days ago
class TestGenerateScorecard:
"""Test scorecard generation."""
def test_generate_scorecard_no_activity(self):
"""Test scorecard generation for agent with no activity."""
with patch("dashboard.services.scorecard.core.collect_events_for_period", return_value=[]):
with patch(
"dashboard.services.scorecard.core.query_token_transactions",
return_value=(0, 0),
):
scorecard = generate_scorecard("kimi", PeriodType.daily)
assert scorecard is not None
assert scorecard.agent_id == "kimi"
assert scorecard.period_type == PeriodType.daily
assert len(scorecard.narrative_bullets) == 1
assert "No recorded activity" in scorecard.narrative_bullets[0]
def test_generate_scorecard_with_activity(self):
"""Test scorecard generation includes activity."""
events = [
Event(type="gitea.push", source="gitea", data={"actor": "kimi", "num_commits": 5}),
]
with patch(
"dashboard.services.scorecard.core.collect_events_for_period", return_value=events
):
with patch(
"dashboard.services.scorecard.core.query_token_transactions",
return_value=(100, 20),
):
scorecard = generate_scorecard("kimi", PeriodType.daily)
assert scorecard is not None
assert scorecard.metrics.commits == 5
assert scorecard.metrics.tokens_earned == 100
assert scorecard.metrics.tokens_spent == 20
class TestGenerateAllScorecards:
"""Test generating scorecards for all agents."""
def test_generates_for_all_tracked_agents(self):
"""Test all tracked agents get scorecards even with no activity."""
with patch("dashboard.services.scorecard.core.collect_events_for_period", return_value=[]):
with patch(
"dashboard.services.scorecard.core.query_token_transactions",
return_value=(0, 0),
):
scorecards = generate_all_scorecards(PeriodType.daily)
agent_ids = {s.agent_id for s in scorecards}
expected = {"kimi", "claude", "gemini", "hermes", "manus"}
assert expected.issubset(agent_ids)
def test_scorecards_sorted(self):
"""Test scorecards are sorted by agent_id."""
with patch("dashboard.services.scorecard.core.collect_events_for_period", return_value=[]):
with patch(
"dashboard.services.scorecard.core.query_token_transactions",
return_value=(0, 0),
):
scorecards = generate_all_scorecards(PeriodType.daily)
agent_ids = [s.agent_id for s in scorecards]
assert agent_ids == sorted(agent_ids)
class TestScorecardRoutes:
"""Test scorecard API routes."""
def test_list_agents_endpoint(self, client):
"""Test GET /scorecards/api/agents returns tracked agents."""
response = client.get("/scorecards/api/agents")
assert response.status_code == 200
data = response.json()
assert "agents" in data
assert "kimi" in data["agents"]
assert "claude" in data["agents"]
def test_get_scorecard_endpoint(self, client):
"""Test GET /scorecards/api/{agent_id} returns scorecard."""
with patch("dashboard.routes.scorecards.generate_scorecard") as mock_generate:
mock_generate.return_value = ScorecardSummary(
agent_id="kimi",
period_type=PeriodType.daily,
period_start=datetime.now(UTC),
period_end=datetime.now(UTC),
metrics=AgentMetrics(agent_id="kimi"),
narrative_bullets=["Test bullet"],
patterns=[],
)
response = client.get("/scorecards/api/kimi?period=daily")
assert response.status_code == 200
data = response.json()
assert data["agent_id"] == "kimi"
assert data["period_type"] == "daily"
def test_get_scorecard_invalid_period(self, client):
"""Test GET with invalid period returns 400."""
response = client.get("/scorecards/api/kimi?period=invalid")
assert response.status_code == 400
assert "error" in response.json()
def test_get_all_scorecards_endpoint(self, client):
"""Test GET /scorecards/api returns all scorecards."""
with patch("dashboard.routes.scorecards.generate_all_scorecards") as mock_generate:
mock_generate.return_value = [
ScorecardSummary(
agent_id="kimi",
period_type=PeriodType.daily,
period_start=datetime.now(UTC),
period_end=datetime.now(UTC),
metrics=AgentMetrics(agent_id="kimi"),
narrative_bullets=[],
patterns=[],
),
]
response = client.get("/scorecards/api?period=daily")
assert response.status_code == 200
data = response.json()
assert data["period"] == "daily"
assert "scorecards" in data
assert len(data["scorecards"]) == 1
def test_scorecards_page_renders(self, client):
"""Test GET /scorecards returns HTML page."""
response = client.get("/scorecards")
assert response.status_code == 200
assert "text/html" in response.headers.get("content-type", "")
assert "AGENT SCORECARDS" in response.text
def test_scorecard_panel_renders(self, client):
"""Test GET /scorecards/panel/{agent_id} returns HTML."""
with patch("dashboard.routes.scorecards.generate_scorecard") as mock_generate:
mock_generate.return_value = ScorecardSummary(
agent_id="kimi",
period_type=PeriodType.daily,
period_start=datetime.now(UTC),
period_end=datetime.now(UTC),
metrics=AgentMetrics(agent_id="kimi", commits=5),
narrative_bullets=["Active across 5 commits this day."],
patterns=["High activity"],
)
response = client.get("/scorecards/panel/kimi?period=daily")
assert response.status_code == 200
assert "text/html" in response.headers.get("content-type", "")
assert "Kimi" in response.text
def test_all_panels_renders(self, client):
"""Test GET /scorecards/all/panels returns HTML with all panels."""
with patch("dashboard.routes.scorecards.generate_all_scorecards") as mock_generate:
mock_generate.return_value = [
ScorecardSummary(
agent_id="kimi",
period_type=PeriodType.daily,
period_start=datetime.now(UTC),
period_end=datetime.now(UTC),
metrics=AgentMetrics(agent_id="kimi"),
narrative_bullets=[],
patterns=[],
),
]
response = client.get("/scorecards/all/panels?period=daily")
assert response.status_code == 200
assert "text/html" in response.headers.get("content-type", "")