"""The tasks roledesk offers, and the order a pull runs them in. pull → extract → embed → score → summarise newsdesk's cascade convention: a cascade is a tuple of task names, and the final job of one task starts the next (`step` is the callback it carries). Nothing is alive between two tasks. Every stage is always in the chain, and a stage that is switched off finds nothing: `extract.enabled: false`, or an `on_ingest` this pull does not satisfy, is an extract stage with no batches whose final job moves straight on. Extract runs before score so the gates read what it filled; before embed too, since embedding does not read its columns and the order costs nothing. Summarise runs last because it reads the scores: it takes only the best `summarise.per_agent` roles of each enabled agent. A batch that failed, or a stage somebody killed, does not stop the chain: the work comes round on the next pull, and a rescore of what did arrive is worth having either way. `pull` is a job as well as a cascade, because a schedule enqueues a job kind and a cascade is started by one: the `pull` job's only work is to ask for the chain. Its default schedule, `every 6h`, is declared here beside it. """ from __future__ import annotations from collections.abc import Callable from dataclasses import replace from functools import partial from typing import Any from app.jobs import embed, extract, pull, score, summarise # noqa: F401 -- registers the jobs from desk.tools import agent from pipeline import NULL, TASKS, RunContext, Tally, Task, declare, job STEP = "app.jobs.cascade:step" CASCADES: dict[str, tuple[str, ...]] = { "pull": ("pull", "extract", "embed", "score", "summarise"), } def _once(config: Any, store: Any) -> list[dict[str, Any]]: """One batch with nothing in its payload: a task that is a single job.""" return [{}] def _extract(cascade: str) -> Task: """`extract` as a stage, reading `on_ingest` when it is one of a pull. `never`, or `auto` with no model reachable, is a stage that finds nothing. Standing on its own, as the button, it reads neither.""" stage = extract.extract_task() if not cascade: return stage find = stage.finder def during_a_pull(config: Any, store: Any) -> list[Any]: when = config.extract.on_ingest if when == "never" or (when == "auto" and not agent.backend(config.agent)): return [] return find(config, store) return replace(stage, finder=during_a_pull) def _summarise(cascade: str) -> Task: """`summarise` as a stage: nothing with no model reachable, so a machine without one pulls in silence rather than failing a batch per pull. Off (`summarise.enabled: false`) is nothing in either case. Standing on its own, as the button, a missing model fails the batch with a notice.""" stage = summarise.summarise_task() if not cascade: return stage find = stage.finder def during_a_pull(config: Any, store: Any) -> list[Any]: if not agent.backend(config.agent): return [] return find(config, store) return replace(stage, finder=during_a_pull) STAGES: dict[str, Callable[[str], Task]] = { "pull": lambda cascade: pull.pull_task(), "extract": _extract, "embed": lambda cascade: Task(kind="embed", finder=_once, label="Embedding roles"), "score": lambda cascade: Task(kind="score", finder=_once, label="Scoring roles for every agent"), "summarise": _summarise, } def task(name: str, *, cascade: str = "") -> Task: """One stage as a `Task`. With `cascade` its final job carries `step`, and the next stage follows; without, it stops when its batches do.""" return replace(STAGES[name](cascade), name=name, callback=STEP if cascade else "", carries={"cascade": cascade, "task": name}) def follows(cascade: str, name: str) -> str: """What runs after `name`, or "" at the end or for an unknown name.""" tasks = CASCADES.get(cascade, ()) if name not in tasks: return "" at = tasks.index(name) return tasks[at + 1] if at + 1 < len(tasks) else "" def step(config: Any, store: Any, tally: Tally, payload: dict[str, Any], *, context: Any) -> dict[str, Any]: """The callback: make the next task. A killed stage is skipped and the chain goes on, as in newsdesk's cascade.""" name, done = payload.get("cascade", ""), payload.get("task", "") following = follows(name, done) if following: context.task(task(following, cascade=name)) out: dict[str, Any] = {"task": done, "next": following} if tally.killed: out["skipped"] = "cancelled" return out def chain(name: str) -> Task: """The first stage of cascade `name`, carrying `step`, so the rest follow.""" return task(CASCADES[name][0], cascade=name) @job("pull", "Pulling every board", resource="http") def run_pull(config: Any, store: Any, *, context: RunContext = NULL) -> dict[str, Any]: """Ask for the pull cascade once this job is done. Its own work is nil. Under `NULL` there is no queue to take the chain, so this raises rather than report a pull that never happened; `app job pull` starts the chain on a queue of its own instead of calling this. """ if not context.task(chain("pull")): raise RuntimeError("no queue to start the pull cascade on") return {"started": " > ".join(CASCADES["pull"])} #: What `app job ` and the Pulls page offer besides `pull`: one stage #: each, on its own. `pull` is not a task here, since it is a job: a name that #: is both would be two buttons on the Pulls page. for _name in ("extract", "embed", "score", "summarise"): TASKS[_name] = partial(task, _name) # ---------------------------------------------------------------- schedules # The default, next to the job it fires. A starting point rather than a # setting: a cadence edited or switched off on the Pulls page survives # every restart (see pipeline/schedule.py). declare("pull", "pull", "every 6h", label="Pull every board, then extract, embed, score and summarise")