LCj xdZddlmZddlmZddlmZddlmZm Z ddl m Z ddl m Z ddlmZdd lmZeZed ej&ej( Zej,j/d d gd d dej0ej2dddd ej5dgej6ddZy)up Celery application instance. This is the entry point for `celery -A app.workers.celery_app worker`. Each worker process, when it starts, loads all 6 ML models into its own memory ONCE (via the worker_process_init signal below) — not per task. This is what makes scaling workers horizontally cheap: spin up more processes, each pays the model-loading cost once at boot, then serves many tasks from warm memory. Separating these workers from the Gunicorn/Uvicorn web workers means ML load (CPU-bound, multi-second) never competes with or blocks web request handling (I/O-bound, sub-100ms for everything except /analyze). )Celery)worker_process_init) get_settings) get_logger setup_logging)model_registry)feature_builder) llm_service)reference_datacrop_ai_worker)brokerbackendjsonUTCT) task_serializeraccept_contentresult_serializertimezone enable_utctask_time_limittask_soft_time_limitworker_prefetch_multiplierworker_max_tasks_per_childtask_acks_latetask_reject_on_worker_lostz app.workersNc ttd}|jdtjt jt jtj|jdy)u Runs once per worker process at startup, before it accepts any tasks. If this raises, the worker process fails to start — which is correct: a worker with no models loaded must never silently pick up analysis jobs. zcelery.worker_initzEInitializing Celery worker process: loading models and reference datazCelery worker process readyN) rrinfor loadr rload_allr init)kwargsloggers CC:\Crop_Prediction\Backend\crop-ai-system\app\workers\celery_app.py init_workerr&9s^O , -F KKWX KK-.)returnN)__doc__celeryrcelery.signalsrapp.core.configrapp.core.logging_configrrapp.models_loader.registryrapp.services.feature_builderr app.services.llm_servicer app.services.reference_datar settingsCELERY_BROKER_URLCELERY_RESULT_BACKEND celery_appconfupdateCELERY_TASK_TIME_LIMITCELERY_TASK_SOFT_TIME_LIMITautodiscover_tasksconnectr&r'r%r=s .(=5806 >   % %  * *  8 33!==  # $#( }o.//r'