Upload production/tests/test_fallback.py

Upload production/docker-compose.m2.yml

Upload production/M2_PRO_MAX_GUIDE.md

Upload production/production_server.py

Upload production/.env.minimal

Upload production/docker-compose.m2.yml

Upload production/pyproject.toml

Upload production/M2_PRO_MAX_GUIDE.md

Upload production/.env.minimal

Upload production/Dockerfile.prod

Upload production/tests/test_fallback.py

Upload production/production_server.py

Upload production/LOCAL_DEPLOYMENT.md

Upload production/k8s/deploy.sh

Upload production/tests/load_test.py

Upload production/tests/test_integration.py

Upload production/k8s/stateful-services.yml

Upload production/helm/ml-intern/values.yaml

Upload production/k8s/deployment-worker.yml

Upload production/helm/ml-intern/Chart.yaml

Upload production/k8s/deployment-api.yml

Upload production/k8s/namespace.yml

Upload production/k8s/secret.yml

Upload production/grafana/dashboards/ml_intern.json

Upload production/k8s/configmap.yml

Upload production/prometheus.yml

Upload production/grafana/datasources/prometheus.yml

Upload production/worker.py

Upload production/requirements.prod.txt

Upload production/nginx.conf

Upload production/init.sql

Upload production/Dockerfile.prod

Upload production/.env.example

Upload production/docker-compose.yml

Upload production/production_server.py

Upload production/README.md

feat: add proactive rate-limit guard for NIM 40 req/min

feat: add rpm_limit=40 hint for NVIDIA NIM local provider

Upload configs/cli_agent_config.json

Upload agent/core/effort_probe.py

Upload agent/core/model_switcher.py

feat: add local model provider support to llm_params.py

initial commit