Judge each agent's best roles against its CV as skills, experience and career, a stage after summarise

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-10-03 22:00:18 +02:00
1 parent 4fc474c437
commit 9960799b96
14 files changed
+866 -44

No files matched your search

+24 -6
View File
@@ -1,7 +1,7 @@
"""The tasks roledesk offers, and the order a pull runs them in.
pull → prep → embed → score → enrich → prep → embed → score → extract → score
→ summarise
→ summarise → judge
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).
@@ -21,7 +21,9 @@ three. 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.
Summarise follows, on the best roles by the same agent's summarise limits,
and judge runs last, reading each agent's best roles against its CV by its
judge limits.
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
@@ -44,7 +46,7 @@ from dataclasses import replace
from functools import partial
from typing import Any
from app.jobs import embed, enrich, extract, prep, pull, score, summarise # noqa: F401 -- registers the jobs
from app.jobs import embed, enrich, extract, judge, prep, pull, score, summarise # noqa: F401 -- registers the jobs
from desk.tools import agent
from pipeline import NULL, TASKS, Notice, RunContext, Tally, Task, declare, job
@@ -52,7 +54,7 @@ STEP = "app.jobs.cascade:step"
CASCADES: dict[str, tuple[str, ...]] = {
"pull": ("pull", "prep", "embed", "score", "enrich", "prep", "embed", "score", "extract",
"score", "summarise"),
"score", "summarise", "judge"),
"enrich": ("enrich", "prep", "embed", "score"),
}
@@ -101,6 +103,21 @@ def _summarise(cascade: str) -> Task:
return replace(stage, finder=during_a_pull)
def _judge(cascade: str) -> Task:
"""`judge` as a stage: nothing with no model reachable, as `_summarise`."""
stage = judge.judge_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,
@@ -110,6 +127,7 @@ STAGES: dict[str, Callable[[str], Task]] = {
"prep": lambda cascade: Task(kind="prep", finder=_once,
label="Mapping the roles' host words"),
"summarise": _summarise,
"judge": _judge,
"enrich": lambda cascade: enrich.enrich_task(),
}
@@ -224,7 +242,7 @@ def enrich_after(queue: Any, score_job: Any) -> Any:
#: 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`.
for _name in ("extract", "embed", "score", "summarise", "prep"):
for _name in ("extract", "embed", "score", "summarise", "judge", "prep"):
TASKS[_name] = partial(task, _name)
@@ -235,4 +253,4 @@ for _name in ("extract", "embed", "score", "summarise", "prep"):
# every restart (see pipeline/schedule.py).
declare("pull", "pull", "every 6h",
label="Pull every board, then map, embed, score, read the best roles' pages, "
"extract, rescore and summarise")
"extract, rescore, summarise and judge against the CVs")