Read role pages in an enrich stage after scoring, best roles first

The pull reads listings only. `enrich` (app/jobs/enrich.py) takes the open
roles without text that an enabled agent ranks ungated in its best
`enrich.top` at `enrich.min_score` or above, best score first, on boards
whose reader has `detail`, within `enrich.per_board` and `enrich.per_run`,
one batch per board. `plugins.ats.read_board_details` reads them and keeps
the per-board state; a read that gave no text is read again after
`enrich.retry_days` (finding 18). Filled roles are upserted, which drops
their vectors, and embed and score follow; `cascade.step` passes over both
when nothing was filled.

The pull cascade is pull, embed, score, enrich, embed, score, extract, score,
summarise. Saving an agent and changing a company's affinity queue the
`enrich` job (enrich, embed, score) behind their rescore; a vote does not.
The stage has a switch, `stage:enrich`, over `enrich.enabled`.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-30 09:53:29 +02:00
1 parent 3adafd8950
commit 77b45a4b0f
10 files changed
+956 -219

No files matched your search

+44 -5
View File
@@ -1,6 +1,6 @@
"""The tasks roledesk offers, and the order a pull runs them in.
pull → embed → score → extract → score → summarise
pull → embed → score → enrich → embed → score → extract → 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).
@@ -11,7 +11,10 @@ Every stage is always in the chain, and a stage that is switched off finds
nothing: a stage switched off (`stages.stage_on`), or an `on_ingest` this pull does not
satisfy, is an extract stage with no batches whose final job moves straight
on. The free stages go first: embed and score cost no tokens, and the score
they produce is what bounds the two that do. Extract reads only the best
they produce is what bounds the rest. Enrich reads the best roles without
text on their own pages (`app/jobs/enrich.py`), and embed and score follow for
the roles it filled; when it filled none, `step` passes over both. Extract
reads only the best
roles of each enabled agent, as deep and as low as that agent's own `limits`
say; the second score then applies the gates to the columns it filled.
Summarise runs last, on the best roles by the same agent's summarise limits.
@@ -23,6 +26,11 @@ 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.
`enrich` is a job and a cascade the same way, `enrich → embed → score`, queued
behind the `score` that follows a change to the ranking other than a pull's
(`enrich_after`): an agent saved, a company's affinity changed. A vote moves
one agent's taste a little and queues neither.
"""
from __future__ import annotations
@@ -32,16 +40,21 @@ 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 app.jobs import embed, enrich, extract, pull, score, summarise # noqa: F401 -- registers the jobs
from desk.tools import agent
from pipeline import NULL, TASKS, Notice, RunContext, Tally, Task, declare, job
STEP = "app.jobs.cascade:step"
CASCADES: dict[str, tuple[str, ...]] = {
"pull": ("pull", "embed", "score", "extract", "score", "summarise"),
"pull": ("pull", "embed", "score", "enrich", "embed", "score", "extract", "score",
"summarise"),
"enrich": ("enrich", "embed", "score"),
}
#: What follows `enrich` for the roles it filled, passed over when it filled none.
REFILL = ("embed", "score")
def _once(config: Any, store: Any) -> list[dict[str, Any]]:
"""One batch with nothing in its payload: a task that is a single job."""
@@ -91,6 +104,7 @@ STAGES: dict[str, Callable[[str], Task]] = {
"score": lambda cascade: Task(kind="score", finder=_once,
label="Scoring roles for every agent"),
"summarise": _summarise,
"enrich": lambda cascade: enrich.enrich_task(),
}
@@ -115,6 +129,10 @@ def step(config: Any, store: Any, tally: Tally, payload: dict[str, Any], *,
chain goes on, as in newsdesk's cascade."""
name, done = payload.get("cascade", ""), payload.get("task", "")
at = int(payload.get("at", -1))
tasks = CASCADES.get(name, ())
if done == "enrich" and not enrich.filled(tally) \
and tasks[at + 1:at + 1 + len(REFILL)] == REFILL:
at += len(REFILL)
following = follows(name, at)
if following:
context.task(task(following, cascade=name, at=at + 1))
@@ -169,6 +187,26 @@ def run_pull(config: Any, store: Any, *, context: RunContext = NULL) -> dict[str
return {"started": " > ".join(CASCADES["pull"]), "run": run}
@job("enrich", "Reading the best roles on their own pages", solo=True, resource="http")
def run_enrich(config: Any, store: Any, *, context: RunContext = NULL) -> dict[str, Any]:
"""Ask for the enrich cascade, `enrich → embed → score`. Its own work is
nil, as the `pull` job's. Under `NULL` there is no queue to take it."""
if not context.task(chain("enrich")):
raise RuntimeError("no queue to start the enrich cascade on")
return {"started": " > ".join(CASCADES["enrich"])}
def enrich_after(queue: Any, score_job: Any) -> Any:
"""Queue the `enrich` job behind `score_job`, the rescore that follows a
change to the ranking, however that score ends. One per score job
(`enrich:after:<id>`), so ten changes answered by one score are one
enrich. None without a score job, or when the queue refuses."""
if score_job is None:
return None
return queue.enqueue("enrich", depends_on=[score_job.id], after="done",
dedup_key=f"enrich:after:{score_job.id}")
#: What `app job <name>` and `/api/jobs` start 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 listed twice by `/api/jobs/kinds`.
@@ -182,4 +220,5 @@ for _name in ("extract", "embed", "score", "summarise"):
# setting: a cadence edited or switched off under Runs survives
# every restart (see pipeline/schedule.py).
declare("pull", "pull", "every 6h",
label="Pull every board, then embed, score, extract, rescore and summarise")
label="Pull every board, then embed, score, read the best roles' pages, "
"extract, rescore and summarise")