gongzhiyongandOmX
10a980b0bf
Define Agent and swarm-specific acceptance evidence, move the reports under docs, and make the homepage point to the current standard, live run, model I/O, and handoff evidence. Constraint: Agent quality standards are configured from industry AI and agent risk references because there is no single accepted swarm-Agent certification standard. Rejected: Treating py_compile or unittest as the primary quality standard | they are evidence collection tools, not the Agent quality standard itself. Confidence: high Scope-risk: moderate Directive: Keep future standard reports under docs/ and keep secrets in ignored local .env files only. Tested: git diff --cached --check; python -B -m py_compile swarm_minimal/*.py examples/*.py tests/*.py; python -B -m unittest discover -s tests; python -u -B examples/run_academic_standard_evaluation.py Not-tested: Did not rerun the full live Azure/NewAPI S07 scenario after moving docs; previous live run 3e8e58ae4e084bc8b90cf5c46f8992f3 passed before the docs relocation. Co-authored-by: OmX <omx@oh-my-codex.dev>
56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
from pathlib import Path
|
|
import json
|
|
import sys
|
|
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
from swarm_minimal.core import InMemorySwarmStore, SwarmCoordinator, Task
|
|
from swarm_minimal.local_env import load_project_env
|
|
from swarm_minimal.newapi_agnet import (
|
|
NewApiChannelConfig,
|
|
build_model_test_agnets,
|
|
discover_newapi_models,
|
|
select_distinct_models,
|
|
)
|
|
|
|
|
|
def main() -> None:
|
|
load_project_env(ROOT)
|
|
config = NewApiChannelConfig.from_env()
|
|
print(json.dumps(config.redacted_summary(), ensure_ascii=False, indent=2))
|
|
|
|
discovered_models = discover_newapi_models(config)
|
|
selected_models = select_distinct_models(discovered_models, count=3)
|
|
print("selected_models:")
|
|
for model in selected_models:
|
|
print(f"- {model}")
|
|
|
|
store = InMemorySwarmStore()
|
|
agents = build_model_test_agnets(config, models=selected_models)
|
|
coordinator = SwarmCoordinator(store=store, agents=agents)
|
|
|
|
goal = "test three NewAPI-backed Agnets with different models"
|
|
run_id = coordinator.submit_goal(goal)
|
|
|
|
# The default goal creates plan/build/verify tasks. For this model test we
|
|
# add one task per model-specific capability so all three Agnets must run.
|
|
for index, model in enumerate(selected_models):
|
|
store.add_task(
|
|
Task(
|
|
kind=f"model_test_{index + 1}",
|
|
input=f"{goal}; model={model}",
|
|
)
|
|
)
|
|
|
|
result = coordinator.run_until_converged(run_id)
|
|
print("run_id:", result.run_id)
|
|
print("accepted_score:", result.accepted_score)
|
|
print("completed_tasks:", result.completed_tasks)
|
|
print("accepted_output:", result.accepted_output)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|