Files
jobboard/config.example.yaml

210 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: location, remote area, seniority,
# languages and deadline (app/jobs/extract.py). Off by default: on the API
# backend every batch of 20 roles is a paid call. On, a pull reads the cut of
# every enabled agent (its limits, see agents below). `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
# summarise_top (an agent's limits) best roles of each enabled agent's two
# orders, What I'm looking for and What fits me, and every role liked or
# saved, when they have no summary yet. 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 cut read against its CV: skills, experience and career 0
# to 10, and 1 to 3 strengths and gaps (app/jobs/judge.py); the CV match, which
# orders What fits me on Roles, weights the three. Off by default. On, each pull
# judges the cut of every enabled agent with a CV and a prompt, once per change
# of its CV, prompts, likes, dislikes or must text, or of the role's 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
# Fetch text: reading a role's own page, for the hosts whose list carries no
# text (app/jobs/fetch_text.py); asks no model. A role is read when it has no
# text and is in the cut of an enabled agent (see limits below), so every role
# the model reads has its text first. `enabled` is only the default for a
# fresh database: the switch under Settings, Sources, Runs (or `app stages
# fetch_text on|off`) overrides it and needs no restart.
fetch_text:
enabled: true
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, each agent's prompts and its CV as vectors, for prompt closeness and
# CV closeness (app/jobs/embed.py). Needs the `embeddings` extra; without it
# `embed` posts a notice and scores leave closeness out. Changing the model
# re-embeds. multilingual-e5-small, not English-only MiniLM, because the corpus
# is European (see docs/decisions.md). 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 (prompt
# closeness), taste (job like) and cv (CV closeness, fit's band when left out):
# 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 levels are
# ranks, 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], cv: [0.77, 0.90]}
# 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. The Search
# agents page lists and edits them afterwards, and the Viewing as select on
# Roles picks one by name. An agent has:
# - name, and enabled (default true; false leaves it out of the scores and the
# pull).
# - prompts, a list of {name, text}, each what the agent looks for; a role is
# ranked by the prompt it is closest to. intent, as in config.yaml, is one
# prompt named after the agent.
# - gates, its fetch gate, each {field, values, mode: require|any|exclude}: a
# require gate is the region (the world), the any gates are one group a role
# must match one of ("in Denmark, or remote"; the location), and an exclude
# gate leaves out the roles that match one of its values (title: the titles
# to leave out). A gate rejects only a role whose column is filled, since
# extract fills the rest for the roles in the cut. A company set to All
# locations skips the any group, one set to All roles the exclude gates on
# title. Fields are place, country, remote, remote_from, seniority,
# function, salary_min, currency, permit, languages, company and title. A
# country is an ISO code, filled from the board's location line; EU is a
# role open anywhere in Europe.
# - weights, the want feed score's, which orders What I'm looking for: {fit:
# 0.6, recency: 0.2, affinity: 0.2, taste: 0.2}, that is prompt closeness,
# newness, company like and job like; taste is how close a role is to the
# ones the agent liked minus the ones it passed. cv_skills, cv_experience and
# cv_career {30, 25, 30} weight the judge's three numbers in the CV match.
# - limits, the analytics filter and the summarise size: {cut_fit_top: 500,
# cut_fit_min: 0.6, cut_cv_top: 150, cut_cv_min: 0.6, summarise_top: 30}, the
# count and the minimum by prompt closeness and by CV closeness, and how deep
# into each order summarise reads. See documentation/ADR Fetch prep and
# score.md.
# 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: {cut_fit_top: 1000, cut_fit_min: 0.5, cut_cv_top: 150, cut_cv_min: 0.6,
# summarise_top: 30}
# - 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}
# 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"}}