Files
jobboard/config.example.yaml
T
WolfandClaude Opus 5.5 c23594507a Score each role's closeness to the agent's CV, let the judge also read the 50 closest the score leaves out, and order CV match's unjudged roles by it
The CV is cut into chunks inside e5's window, embedded like a prompt and
cached per agent under a hash of the model, chunking and text. A role's
cv_fit (scores.cv_fit, migration 31) is its best chunk cosine, scaled with
its own calibration band: fit's clipped 88 of agent 2's ungated roles to 1.
It is no term of the Agent match score. judge_cv_top (default 50) sits
beside judge_top and judge_min on the agents page and card.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-03 23:35:21 +02:00

216 lines
11 KiB
YAML

# roledesk configuration. The app reads --config, else $APP_CONFIG, else
# config.yaml beside the checkout (committed: these defaults plus the starter
# agents). Every value below is the default, so a copy with nothing changed
# behaves exactly like no file at all. An unknown key is an error, not a
# shrug; see app/config.py.
server:
# 0.0.0.0 in a container -- the proxy is what is in front of it.
host: 127.0.0.1
port: 8790
# The SQLite file: roles, companies, subscriptions, applications, agents and
# scores, the job queue and its schedules, the notice log, and auth's
# sessions. Not shared with newsdesk.
database: roledesk.db
# What a clock on screen means, and what `daily at 06:00` is 06:00 in.
timezone: Europe/Berlin
log_level: INFO
# One password on a public hostname; see auth/README.md and
# docs/password-protection.md. The password is never in this file.
auth:
enabled: auto # auto: open on loopback, locked on anything else
session_days: 30
secure_cookie: auto # always, behind a TLS-terminating proxy
rp_id: "" # roledesk.example.com -- passkeys are bound to it
rp_name: app # what the authenticator shows you
origin: "" # https://roledesk.example.com
password_env: APP_PASSWORD
cookie: app_session # unique per app sharing a hostname
# Any .py file in these directories defining a desk `Source` subclass is a
# plugin. A plugin imports `desk` only.
plugin_paths:
- plugins
# Workers per resource class. `http` is wide because a fetch is mostly waiting.
workers:
llm: 4
http: 8
cpu: 1
# Who answers when a job needs a model. See desk/tools/agent.py; needs the
# `agent` extra.
agent:
backend: auto # auto | api | claude_code | off
model: "" # overrides extract.model, summarise.model and judge.model when set
timeout: 300.0 # seconds for one model call, either backend
max_tokens: 8192 # the answer's cap per call
cli_path: "" # where the `claude` binary is, if not on PATH
# Title and description in, gate columns out (app/jobs/extract.py). Off by
# default: on the API backend every batch of 20 roles is a paid call. On, a
# pull reads only the best roles of every enabled agent, as deep and as low
# as that agent's own limits say (see agents below), after a first score; a
# second score then applies the gates to what was filled. `enabled` is only the
# default for a fresh database: the switch under Settings, Sources, Runs (or
# `app stages extract on|off`) overrides it and needs no restart.
extract:
enabled: false
model: claude-haiku-4-5-20251001 # agent.model wins when set
batch_size: 20 # roles per model call
on_ingest: auto # auto: in a pull when a model is reachable | always | never
thinking: off # off | adaptive
# About 60 words on a role: what it is, the stack, where, the pay if stated
# (app/jobs/summarise.py). Off by default. On, each pull summarises the best
# roles of every enabled agent that have none yet, by that agent's limits, so
# the cost stays bounded however many roles are open. The Summarise button on
# a role's page asks for that one role either way. `enabled` is only the
# default for a fresh database: the switch under Settings, Sources, Runs (or
# `app stages summarise on|off`) overrides it and needs no restart.
summarise:
enabled: false
model: claude-haiku-4-5-20251001 # agent.model wins when set
batch_size: 10 # roles per model call
thinking: off # off | adaptive
# on_ingest (auto | always | never) is accepted here and ignored: a pull
# runs summarise when it is on and a model is reachable (app/jobs/cascade.py).
# Only extract reads it.
# Each search agent's best roles read against its CV: skills, experience and
# career 0 to 100, a total, and 1 to 3 strengths and gaps (app/jobs/judge.py),
# for the CV match order on Roles. Off by default. On, each pull judges
# the best roles of every enabled agent with a CV, by that agent's judge
# limits, and only those not judged yet or judged from another CV, prompt,
# avoid or must text, or role text. The CV rides in every call, so batches are
# small. `enabled` is only the default for a fresh database: the switch under
# Settings, Sources, Runs (or `app stages judge on|off`) overrides it and needs
# no restart. on_ingest is accepted and ignored, as for summarise.
judge:
enabled: false
model: claude-haiku-4-5-20251001 # agent.model wins when set
batch_size: 5 # roles per model call
thinking: off # off | adaptive
# Reading the best roles on their own pages, for the hosts whose list carries
# no text (app/jobs/enrich.py); asks no model. A role is read when it has no
# text and an enabled agent with a prompt ranks it ungated among its best
# `top` and at `min_score` or above. `enabled` is only the default for a fresh
# database: the switch under Settings, Sources, Runs (or `app stages enrich
# on|off`) overrides it and needs no restart.
enrich:
enabled: true
top: 500 # rank depth per agent
min_score: 0.5 # 0..1, the score bar
per_board: 200 # reads per board and run
per_run: 1000 # reads per run
retry_days: 7 # days before a page that gave no text is read again
# A role and each agent's prompts as vectors, for the fit term of a score
# (app/jobs/embed.py). Needs the `embeddings` extra; without it `embed` posts
# a notice and scores leave fit out. Changing the model re-embeds.
# multilingual-e5-small, not English-only MiniLM, because the corpus is now
# European: measured against the "Copenhagen engineering" agent's intent, it
# separates engineering from non-engineering roles better, especially among
# Danish-country roles (see docs/decisions.md), for about 3x the CPU time. An
# e5 model's "query: " / "passage: " prefixes are added automatically, keyed
# off this name.
# calibration maps a model's cosines to 0..1 levels, as [lo, hi] for fit and
# for taste: lo is 0, hi is 1, clipped outside. multilingual-e5-small has
# built-in constants (app/config.py, CALIBRATION); an entry here replaces
# them for that model. A model with none is min-max scaled per run instead,
# so its fit is a rank, not a level, and the log says so.
embed:
model: intfloat/multilingual-e5-small
per_run: 50000
calibration: {}
# intfloat/multilingual-e5-small: {fit: [0.75, 0.88], taste: [-0.14, 0.19]}
# One block per plugin, keyed by the plugin's name. The ats and search plugins
# read their boards and searches from the subscriptions table, so they need
# none, except the key an adzuna search needs (or ADZUNA_APP_ID and
# ADZUNA_APP_KEY in the environment, which keeps it out of this file).
sources: {}
# `enabled` is a key every plugin's block takes, but the pull builds its ats and
# search plugins from the subscriptions and does not read it: switch a board
# or a search off on the Sources page instead.
# search:
# adzuna: {app_id: "...", app_key: "..."}
# Starter search agents, imported once into an empty `agents` table. Each gate
# is {field, values, mode: require|any|prefer, weight}; the any gates are one
# group a role must match one of ("in Denmark, or remote"), and a gate rejects
# only a role whose column is filled, since extract fills the rest for the
# roles that rank. 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, taste:
# 0.2}; taste is how close a role is to the ones the agent liked minus the
# ones it passed. A country is an ISO code, filled from the board's location
# line; EU is a role open anywhere in Europe.
# limits is how deep into this agent's ranking the model stages read, each a
# top N (the backstop) and a minimum score (the real stop): extract reads the
# best extract_top roles at extract_min or more, summarise the best
# summarise_top at summarise_min or more, and judge the best judge_top at
# judge_min or more for an agent with a CV, and the judge_cv_top ungated roles
# closest to the CV that those leave out. Fit is a calibrated level, so a bar
# means the same in every run: a fresh role with the worst fit scores about
# 0.27 on the default weights, a perfect one about 0.87. The defaults are
# {extract_top: 500, extract_min: 0.55, summarise_top: 30, summarise_min:
# 0.65, judge_top: 150, judge_min: 0.55, judge_cv_top: 50}; measured for "Copenhagen engineering" on 16,841 open roles, 0.55
# admits about 300 roles to extract and 0.65 about 35 to summarise. A wide
# monitoring search lowers the bars and raises the counts, a narrow hunt the
# reverse. An agent without a prompt that has text has no fit and feeds
# neither stage.
# prompts is a list of {name, text}, each what the agent looks for; a role's
# fit is its best prompt's, so one agent can hunt several kinds of role
# without blending them into one paragraph. Votes, gates and limits stay the
# agent's, shared by its prompts. intent, as in config.yaml, is one prompt
# named after the agent.
# enabled (default true) leaves an agent out of the scores and the pull when
# false. The Search agents sub-tab lists and edits them; the order menu on
# Roles picks one by name. Two more, beside the starter in config.yaml:
agents: []
# - name: Remote from Europe
# prompts:
# - name: Platform lead
# text: >-
# Staff or lead engineer role, fully remote from Europe. Platform and
# infrastructure work, distributed systems, developer tooling,
# technical leadership across teams.
# - name: Forward deployed
# text: >-
# Forward deployed or solutions engineering lead, fully remote from
# Europe. Hands-on with customers' systems, owns technical delivery.
# gates:
# - {field: remote, values: [remote], mode: require}
# - {field: country, values: [AT, BE, BG, HR, CY, CZ, DK, EE, FI, FR, DE, GR, HU, IE, IT,
# LV, LT, LU, MT, NL, PL, PT, RO, SK, SI, ES, SE, IS, LI, NO,
# GB, CH, EU], mode: require}
# limits: {extract_top: 1000, extract_min: 0.45, summarise_top: 50, summarise_min: 0.6}
# - name: Europe hybrid
# intent: >-
# Senior backend or platform engineer in a European tech hub, hybrid or
# remote-first. Python and Go, distributed systems, cloud infrastructure.
# gates:
# - {field: country, values: [AT, BE, BG, HR, CY, CZ, DK, EE, FI, FR, DE, GR, HU, IE, IT,
# LV, LT, LU, MT, NL, PL, PT, RO, SK, SI, ES, SE, IS, LI, NO,
# GB, CH, EU], mode: require}
# - {field: remote, values: [hybrid, remote], mode: prefer, weight: 0.05}
# Starter searches, imported once while there are no `search` subscriptions.
# provider is a search reader: jobindex (Denmark, no key: q, area, pages),
# adzuna (the UK and most of the EU, a free key: q, country, where, pages) or
# platsbanken (Sweden, no key: q, region: the id of a län, or empty),
# freehire (many countries, no key: q, country: lower-case ISO codes, comma
# separated, remote: a work mode), jobnet (Denmark, no key: q, region: one of
# its five region ids) or jobbank (Akademikernes Jobbank, Denmark, no key: q,
# region: an amt id, remote: helt or delvist). See plugins/readers/.
searches: []
# - {name: Head of data, provider: freehire, params: {q: head of data, country: dk}}
# - {name: Data science, provider: jobnet, params: {q: data science, region: HovedstadenOgBornholm}}
# - {name: Data director, provider: jobbank, params: {q: data director, region: "2"}}