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

+4 -7
View File
@@ -20,7 +20,7 @@ import logging
from datetime import UTC, datetime
from typing import Any
from pipeline import NULL, RunContext, TASKS, Tally, Task, job
from pipeline import NULL, RunContext, Tally, Task, job
from roledesk.config import Config
from roledesk.storage import Store
@@ -103,11 +103,8 @@ def close_boards(config: Config, store: Store, tally: Tally, *,
return {"boards": answered, "failed": failed, "roles": roles, "closed": closed}
def _pull_task() -> Task:
def pull_task() -> Task:
"""The pull on its own. `roledesk.jobs.cascade` makes it the first stage
of the chain that `TASKS["pull"]` starts."""
return Task(kind="pull_batch", finder=_boards, name="pull",
label="Reading every board", settle=SETTLE)
#: Offered as `roledesk job pull` and to `<desk-jobs>`'s Pull button, the same
#: way newsdesk's cascade stages register themselves in `TASKS`.
TASKS["pull"] = _pull_task