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

+18
View File
@@ -26,5 +26,23 @@ extract:
enabled: false
model: claude-haiku-4-5-20251001
# A role and each agent's intent as vectors, for the fit term of a score
# (roledesk/jobs/embed.py). Needs sentence-transformers; without it `embed`
# posts a notice and scores leave fit out. Changing the model re-embeds.
embed:
model: sentence-transformers/all-MiniLM-L6-v2
per_run: 50000
# Starter search agents, imported once into an empty `agents` table. Each gate
# is {field, values, mode: require|prefer, weight}; fields are place, country,
# remote, seniority, function, salary_min, currency, permit, languages and
# company. weights default to {fit: 0.6, recency: 0.2, affinity: 0.2}.
agents:
- name: Berlin backend
intent: Senior backend engineer, Python services and PostgreSQL.
gates:
- {field: place, values: [Berlin], mode: require}
- {field: remote, values: [hybrid, remote], mode: prefer, weight: 0.2}
# One block per plugin. Empty until the ats plugin lands.
sources: {}