Spaces:
Running on Zero
Running on Zero
File size: 7,286 Bytes
123559e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 | import os
import unittest
from types import SimpleNamespace
from unittest.mock import patch
from app.routers.calls import _evaluation_summary, _pipeline_progress
def _job(status, stage):
return SimpleNamespace(status=status, stage=stage)
class PipelineProgressTests(unittest.TestCase):
def test_active_stage_completes_every_prior_enabled_step(self):
with patch.dict(
os.environ,
{
"ENABLE_ACOUSTIC": "1",
"EVALUATOR_V2_SHADOW": "1",
},
):
progress = _pipeline_progress(
_job("processing", "evaluating_v2_requirements")
)
states = {
stage["id"]: stage["state"]
for stage in progress["stages"]
}
self.assertEqual(states["evaluation"], "completed")
self.assertEqual(states["evidence"], "completed")
self.assertEqual(states["requirements"], "active")
self.assertEqual(states["findings"], "pending")
self.assertEqual(states["publish"], "pending")
self.assertEqual(
progress["current_stage_label"],
"Assess requirements",
)
def test_forced_transcription_starts_in_the_queue(self):
progress = _pipeline_progress(
_job("queued", "force_uploaded")
)
self.assertEqual(progress["current_stage_id"], "queued")
self.assertEqual(progress["percent"], 0)
self.assertEqual(progress["stages"][0]["state"], "active")
def test_disabled_optional_stages_are_marked_skipped(self):
with patch.dict(
os.environ,
{
"ENABLE_ACOUSTIC": "0",
"EVALUATOR_V2_SHADOW": "0",
},
):
progress = _pipeline_progress(
_job("processing", "evaluating")
)
states = {
stage["id"]: stage["state"]
for stage in progress["stages"]
}
self.assertEqual(states["acoustic"], "completed")
self.assertEqual(states["evidence"], "skipped")
self.assertEqual(states["requirements"], "skipped")
self.assertEqual(states["findings"], "skipped")
self.assertEqual(states["decision"], "skipped")
self.assertEqual(states["presentation"], "skipped")
self.assertEqual(states["evaluation"], "active")
def test_success_marks_enabled_pipeline_complete(self):
with patch.dict(
os.environ,
{
"ENABLE_ACOUSTIC": "1",
"EVALUATOR_V2_SHADOW": "0",
},
):
progress = _pipeline_progress(_job("succeeded", "done"))
enabled_states = [
stage["state"]
for stage in progress["stages"]
if stage["state"] != "skipped"
]
self.assertEqual(set(enabled_states), {"completed"})
self.assertEqual(progress["percent"], 100)
def test_failure_marks_current_stage(self):
with patch.dict(
os.environ,
{
"ENABLE_ACOUSTIC": "1",
"EVALUATOR_V2_SHADOW": "0",
},
):
progress = _pipeline_progress(
_job("failed", "segmenting")
)
current = next(
stage
for stage in progress["stages"]
if stage["id"] == "segments"
)
self.assertEqual(current["state"], "failed")
class EvaluationSummaryTests(unittest.TestCase):
def test_success_uses_evaluator_presentation_not_legacy_scores(self):
run = SimpleNamespace(
status="succeeded",
created_at=None,
payload={
"status": "succeeded",
"evaluator_version": "v2-policy-test",
"decision": {
"decision_status": "complete",
"attention_required": True,
},
"presentation": {
"state": "needs_attention",
"evaluation_status": "complete",
"attention_required": True,
"manager_questions": [
{
"question_id": "call.request",
"answer": "yes",
"summary": "Request confirmed.",
"evidence_ids": ["evidence-request"],
},
{
"question_id": "call.process",
"answer": "partly",
"summary": "One process concern.",
"evidence_ids": ["evidence-process"],
},
{
"question_id": "call.experience",
"answer": "yes",
"summary": "Experience handled.",
"evidence_ids": [],
},
{
"question_id": "call.outcome",
"answer": "yes",
"summary": "Outcome confirmed.",
"evidence_ids": ["evidence-outcome"],
},
],
"primary_reasons": [{"finding_id": "finding-a"}],
"additional_reason_count": 1,
"checklist": [
{"status": "demonstrated"},
{"status": "incorrect"},
{"status": "not_demonstrated"},
],
"acoustic_context": {
"status": "limited",
"coverage_label": "Audio support on 2 of 3 segments",
},
},
},
)
summary = _evaluation_summary("call-a", "banking", run)
self.assertTrue(summary["evaluation_available"])
self.assertTrue(summary["attention_required"])
self.assertEqual(summary["evaluation_state"], "needs_attention")
self.assertEqual(summary["result"], "review")
self.assertEqual(summary["aspects"]["request"]["state"], "ok")
self.assertEqual(summary["aspects"]["process"]["state"], "concern")
self.assertEqual(summary["concern_count"], 2)
self.assertEqual(summary["checklist_counts"]["demonstrated"], 1)
self.assertEqual(summary["checklist_counts"]["incorrect"], 1)
self.assertEqual(
summary["checklist_counts"]["not_demonstrated"],
1,
)
self.assertEqual(summary["acoustic_status"], "limited")
def test_domain_without_profile_is_not_reported_as_evaluated(self):
summary = _evaluation_summary(
"call-b",
"health",
SimpleNamespace(
status="unsupported_domain",
created_at=None,
payload={"status": "unsupported_domain"},
),
)
self.assertFalse(summary["evaluation_available"])
self.assertTrue(summary["evaluation_supported"])
self.assertEqual(summary["evaluation_state"], "unsupported")
if __name__ == "__main__":
unittest.main()
|