"""The work roledesk queues. Importing this package registers every job, every task in `pipeline.TASKS` and the default schedule in `pipeline.SCHEDULES`. pull.py read every board and search and store the roles they yield prep.py the `prep` stage: `app.prep` over what a pull stored, then the fold extract.py title and description into the gate columns, on Haiku embed.py one vector per open role, for fit score.py every open role scored for every enabled search agent summarise.py about 60 words on each of the best roles, on Haiku cascade.py pull → prep → embed → score → ... → summarise, what `TASKS` offers, the `pull` job a schedule fires, and that schedule stages.py whether extract and summarise run: the switch, else config.yaml sources.py what a pull reads, changed by hand: boards and searches added, switched on or off discover.py which ATS a company's careers site runs on, from its pages posting.py one role's posting page fetched as text, on demand reach.py which countries a pull asks each big board for, from the agents limits.py what limits a board's read, in words, for the Companies list """ from __future__ import annotations from typing import Any from app.jobs import (cascade, discover, embed, extract, limits, posting, pull, reach, score, sources, stages, summarise) from app.jobs.pull import search_target, seed_searches from app.jobs.score import seed_agents #: What `JobQueue(bootstrap=...)` and `pipeline.worker --bootstrap` are given. BOOTSTRAP = "app.jobs:bootstrap" def bootstrap(config_path: str = "") -> tuple[Any, Any]: """`(config, store)` from the config file alone, for a job run in its own process or by `python -m pipeline.worker`. Importing this module is what fills `JOBS`, which is why the worker is handed a name rather than a queue.""" from app import config as config_mod from app.storage import Store config = config_mod.load(config_path or None) return config, Store(config.database) __all__ = ["BOOTSTRAP", "bootstrap", "cascade", "discover", "embed", "extract", "limits", "posting", "pull", "reach", "score", "search_target", "seed_agents", "seed_searches", "sources", "stages", "summarise"]