gongzhiyongandOmX
a4d771ede5
Add a concrete 0-100 swarmness/compliance score, local large-scale stress, and 3000 TPM budget acceptance so the repo can say when it is a swarm by measured criteria instead of prose alone. Constraint: user required Chinese docs, explicit scenarios, parameters, formulas, pass/fail lines, and git upload. Rejected: prose-only PASS reports | they did not answer whether the system is a swarm with a concrete score. Confidence: high Scope-risk: moderate Directive: keep production runtime claims separate from local minimal swarm acceptance scores. Tested: py_compile swarm_minimal examples tests; unittest discover -s tests 45 tests; run_swarm_compliance_score.py; run_tpm_budget_acceptance.py; run_academic_standard_evaluation.py; git diff --check; docs/script secret-pattern scan. Not-tested: live S07 and production Kubernetes/NewAPI provider-rate-limit stress were not rerun in this upload step. Co-authored-by: OmX <omx@oh-my-codex.dev>
47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
import unittest
|
|
|
|
from examples.run_tpm_budget_acceptance import TpmConfig, run_acceptance
|
|
|
|
|
|
class TpmBudgetAcceptanceTest(unittest.TestCase):
|
|
def test_exact_3000_tpm_budget_passes_without_overrun(self) -> None:
|
|
report = run_acceptance(
|
|
TpmConfig(
|
|
target_tpm=3000,
|
|
agent_count=6,
|
|
task_count=60,
|
|
tokens_per_task=50,
|
|
)
|
|
)
|
|
|
|
self.assertEqual(report["status"], "PASS")
|
|
self.assertEqual(report["summary"]["total_reserved_tokens"], 3000)
|
|
self.assertEqual(report["summary"]["simulated_minutes"], 1)
|
|
self.assertEqual(report["summary"]["max_tokens_in_any_minute"], 3000)
|
|
self.assertEqual(report["summary"]["over_budget_windows"], {})
|
|
self.assertEqual(report["summary"]["completed_tasks"], 60)
|
|
self.assertEqual(report["summary"]["failed_tasks"], 0)
|
|
self.assertEqual(report["summary"]["duplicate_claims"], 0)
|
|
self.assertEqual(report["summary"]["participating_agents"], 6)
|
|
|
|
def test_budget_rolls_forward_without_exceeding_window(self) -> None:
|
|
report = run_acceptance(
|
|
TpmConfig(
|
|
target_tpm=3000,
|
|
agent_count=4,
|
|
task_count=61,
|
|
tokens_per_task=50,
|
|
)
|
|
)
|
|
|
|
self.assertEqual(report["status"], "PASS")
|
|
self.assertEqual(report["summary"]["total_reserved_tokens"], 3050)
|
|
self.assertEqual(report["summary"]["simulated_minutes"], 2)
|
|
self.assertEqual(report["summary"]["max_tokens_in_any_minute"], 3000)
|
|
self.assertEqual(report["summary"]["over_budget_windows"], {})
|
|
self.assertEqual(report["tokens_by_minute"], {"0": 3000, "1": 50})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|