Files
jobboard/config.example.yaml
T
2026-09-30 15:44:32 +02:00

193 lines
9.9 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 and summarise.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.
# 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 two 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. 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}; 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). See
# plugins/readers/.
searches: []