Score roles per search agent, and run pull into extract, embed and score

embed stores one vector per open role; score rates every open role for
every enabled agent from require and prefer gates, fit against the
agent's intent, recency and company affinity, keeping gated rows with a
reason. Schema v3 adds vectors and the cached intent vector. The page
gets an agent order, the score on each row, and an Agents tab. Two
starter agents in roles.yaml are imported once.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-23 12:14:21 +02:00
1 parent 4dfb8831aa
commit bc60324fab
22 files changed
+1457 -44

No files matched your search

+9 -3
View File
@@ -1,12 +1,17 @@
"""The work roledesk queues. Importing this package registers every job.
"""The work roledesk queues. Importing this package registers every job and
every task in `pipeline.TASKS`.
pull.py read every configured plugin and store the roles it yields
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
cascade.py pull → extract → embed → score, and what `TASKS` offers
"""
from __future__ import annotations
from roledesk.jobs import extract, pull
from roledesk.jobs import cascade, embed, extract, pull, score
from roledesk.jobs.score import seed_agents
#: What `JobQueue(bootstrap=...)` and `pipeline.worker --bootstrap` are given.
BOOTSTRAP = "roledesk.jobs:bootstrap"
@@ -22,4 +27,5 @@ def bootstrap(config_path: str = "") -> tuple[object, object]:
return config, Store(config.database)
__all__ = ["BOOTSTRAP", "bootstrap", "extract", "pull"]
__all__ = ["BOOTSTRAP", "bootstrap", "cascade", "embed", "extract", "pull", "score",
"seed_agents"]