From c3bc2cd7f3a819f3d0767d34f83e062072ef62eb Mon Sep 17 00:00:00 2001 From: Wolf Date: Mon, 5 Oct 2026 09:32:43 +0200 Subject: [PATCH] Say Search agents, Viewing as and the want feed score in the config comments, add the cv calibration band and shorten the comments that restated the ADR Co-Authored-By: Claude Fable 5.1 --- config.example.yaml | 123 +++++++++++++++++++++----------------------- config.yaml | 8 +-- 2 files changed, 62 insertions(+), 69 deletions(-) diff --git a/config.example.yaml b/config.example.yaml index 9002691..bfe014e 100644 --- a/config.example.yaml +++ b/config.example.yaml @@ -51,11 +51,10 @@ agent: 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 cut of every enabled agent (its limits, see agents -# below), after a first score; a second score then applies the fetch gate and -# the cut to what was filled. `enabled` is only the +# 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: @@ -66,12 +65,11 @@ extract: 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 top -# of every enabled agent's feed that has none yet, the best summarise_top (its -# limits) by the want feed score and the best summarise_top by the match -# order (CV match, then CV closeness), and every role liked or saved, 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 +# (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: @@ -84,12 +82,12 @@ summarise: # Only extract reads it. # Each search agent's cut read against its CV: skills, experience and career 0 -# to 10, a total 0 to 100, 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 cut of -# every enabled agent with a CV and a prompt, and only the roles not judged -# yet or judged from another CV, prompt, like, 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 +# 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: @@ -110,25 +108,23 @@ fetch_text: 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. +# 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]} +# 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 @@ -141,39 +137,36 @@ sources: {} # search: # adzuna: {app_id: "...", app_key: "..."} -# Starter search agents, imported once into an empty `agents` table. The gates -# are the agent's fetch gate, each {field, values, mode: require|any|exclude}: -# a require gate is the region, the any gates are one group a role must match -# one of ("in Denmark, or remote"), the place part, 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. weights are the final -# score's, the feed's order, default {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 the agent's cut, the roles that get fetch text, extract and -# judge: the best cut_fit_top by fit level at cut_fit_min or more, then the -# best cut_cv_top by CV closeness at cut_cv_min or more that the first list -# leaves out, then every role liked or saved. Both levels are calibrated, so -# a minimum means the same in every run, and a liked company's roles sit -# about 0.05 higher, a favourite's about 0.1. summarise_top is how deep into -# each order, want and match, summarise reads. The defaults are -# {cut_fit_top: 500, cut_fit_min: 0.6, cut_cv_top: 150, cut_cv_min: 0.6, -# summarise_top: 30}. For a broad agent the count stops a list, for a narrow -# one the minimum. An agent without a prompt that has text has no fit, so -# nothing of it is in the cut by fit. -# 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: +# 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: diff --git a/config.yaml b/config.yaml index b2bb3c5..7a46af2 100644 --- a/config.yaml +++ b/config.yaml @@ -27,10 +27,10 @@ embed: model: intfloat/multilingual-e5-small sources: {} # The starter ranking, imported once into an empty table. Edit it under -# Settings, Ranking afterwards; this list is not read again. EU in a country -# gate is a role open anywhere in Europe ("Remote - Europe", "EMEA"). Which -# roles get fetch text, extract and judge is each agent's cut, its `limits`, see -# config.example.yaml, which has two more agents. +# Settings, Search agents afterwards; this list is not read again. EU in a +# country gate is a role open anywhere in Europe ("Remote - Europe", "EMEA"). +# Which roles get fetch text, extract and judge is each agent's cut, its +# `limits`, see config.example.yaml, which has two more agents. agents: - name: Copenhagen engineering intent: >-