Commit Graph
43 Commits
Author SHA1 Message Date
WolfandClaude Sonnet 5.5 8c6cbdf002 Give an agent a soft profile of likes and dislikes and take the must-haves off the form (wp-likes)
Add agents.like_text (migration 30) beside avoid_text, now shown as "What I don't like". The judge reads both under <likes> and <dislikes>, its career rubric judges against the prompts, the likes and the dislikes, and FORMAT 3 makes earlier judgements be made again. The form drops the must-haves box and no longer sends must_text, so a stored one is kept and still caps career in code.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 22:48:46 +02:00
WolfandClaude Sonnet 5.5 001fc9002b Let the model report a verdict per must-have and cap career at 39 in code when one is broken
The judge numbers an agent's must-haves (one per line) and answers met, broken or unclear for each; career is stored as the model gave it and counts as at most BROKEN_CAP when a role is served, in cv_score, Store.judgement and the SQL of Best CV match. Migration 29 adds role_judgements.musts and broken; the judge's input_key carries a format version so earlier judgements are made again. The reader lists the must-haves with their verdicts and the cap.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 22:40:54 +02:00
WolfandClaude Sonnet 5.5 585c332d74 Make the three CV match weights a per-agent setting, applied when a role is served
cv_skills, cv_experience and cv_career live in agents.weights (30, 25, 30 by
default), edited on the Search agents page beside fit and recency. cv_score is
worked out at read time in the feed order, the row and the reader, so changing
them asks the model for nothing and leaves the judge's input_key alone.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 22:25:44 +02:00
WolfandClaude Sonnet 5.5 8f5c4666bc Edit an agent's CV, languages, avoid and must-have texts and the judge limits on the Search agents page
A Your CV fieldset in the edit form: the CV as text or read from a .md/.txt
file, language rows of a code and a level with Suggest languages from the
CV, and the Avoid / drains me and Must-haves and deal-breakers texts. The
judge limits sit beside extract and summarise, the card's limits line gets a
judge clause and one more line says whether a CV is set and its languages.
Save sends all four fields, and the card switch re-posts the row with them.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 22:18:32 +02:00
WolfandClaude Opus 5.5 9960799b96 Judge each agent's best roles against its CV as skills, experience and career, a stage after summarise
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-03 22:00:18 +02:00
WolfandClaude Opus 5.5 dd733c9fb5 Say that a Jobnet query requires every word, as a live count shows, not that it matches loosely
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-03 21:17:13 +02:00
WolfandClaude Sonnet 5.5 6e6e655203 Wire freehire, Jobnet and Akademikernes Jobbank into the CLI, the Sources form, dupes and the docs
Provider names, the CLI's choices and the dupes rule's search hosts now come from readers.PROVIDERS, and the regions, work modes and remote words from the modules' REGIONS, MODES and REMOTE, read with getattr so main works before and after the readers merge.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 12:24:34 +02:00
Wolf 5c3c187dca Merge the remote pages: scope line, Remote select, remote chips and badge (wp-remote-b)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	app/static/agents.js
2026-09-30 16:22:22 +02:00
WolfandClaude Fable 5.1 6451f503f2 Show and filter the limits on the Companies list, list the traits on Sources
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-30 16:00:45 +02:00
WolfandClaude Opus 5.5 888586c29b Make the agent's scope a line of its own: Only roles in Europe, chosen countries or Everywhere, read and written as the require gate on country
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 15:31:40 +02:00
WolfandClaude Opus 5.5 8c6ea0ffb6 Leave out titles by phrase: an exclude gate mode and a title gate field
A role whose title holds one of the agent's phrases as whole words is gated
with the phrase as its reason, a favourite's too. The agent form has a
Leave out titles line under Where. function = sales could not do it, since
the classifier files Solutions Engineer and pre-sales under sales.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 15:27:43 +02:00
WolfandClaude Opus 5.5 1c7bc72198 Replace the agent's remote scope by Remote, open to someone in: chips written as one remote_from gate
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 15:23:04 +02:00
WolfandClaude Opus 5.5 e03305ff87 Say how fetch terms are separated and that they match the whole ad
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:07:25 +02:00
WolfandClaude Opus 5.5 06ff9f549b List unlinked places and unmapped words under Sources, fix them in code with the unmapped skill
Settings > Sources > Unmapped shows the place texts no place resolves, with
their roles' countries and companies, and the host words no table maps, and
copies both as text. Prep fingerprints places.seed(), so a town or spelling
added to the code is seeded and every open role is mapped again at the next
prep. app prep unlinked lists the places on the command line.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:06:22 +02:00
WolfandClaude Opus 5.5 e52857dea5 Split the All tag into two company overrides: All countries and All roles (WP L)
Fetching has two filters, and a company now overrides each on its own.
All countries (companies.all_countries) is the old All roles tag: its big
boards are read with the agents' wide reach. All roles (companies.all_roles,
new meaning) drops the agents' fetch terms and any later role filter.

- Migration 24 copies the old tag to all_countries and keeps all_roles for
  those companies, and moves a board's {"terms": false} to its company.
- The runner no longer reads {"terms": false}; the plan leaves the terms out
  for a company set to All roles.
- POST /api/companies/{key}/all-countries and /all-roles, each queueing a
  pull when turned on; CompanyOut carries both.
- Two toggles replace All on the Companies row, the reader and the Roles
  strip; the reach line states countries and role types in plain words;
  the filter select gets both options.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 12:50:45 +02:00
WolfandClaude Opus 5.5 0fd45b333a Fetch terms narrow what big boards read with the wide reach send (WP F2)
An agent has fetch_terms (migration 23, API, a chip field in the agent
editor). The terms of a pull are the union over the enabled agents, none
when one of them has none. They go only to wide reads: a company tagged All
roles, or a reach ask_for drops as too many countries for a one host; a
board's {"terms": false} switches them off. SmartRecruiters q,
SuccessFactors q, Workday searchText, Phenom keywords, Eightfold query and
Oracle keyword declare query="one"; the runner makes one series per term
times the country series, drops the places first over MAX_SERIES, then the
terms. A term read is narrowed: it writes no ats:size, closes nothing and
prunes no per-role state, and the 10% guard holds it to its own
fingerprint. The Companies reach line counts the terms.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 11:59:27 +02:00
WolfandClaude Opus 5.5 5d5b7e7d3f Tag a company All roles to read its big boards with the agents' wide reach; favourite scores only
Migration 21 adds companies.all_roles, tags every favourite of any agent and each company whose board had params {"reach": "all"} (logged per board, the param removed). reach.plan reads a tagged company's boards with the union of the enabled agents' require reach and the base reach; favourite no longer widens the fetch. POST /api/companies/{key}/all-roles sets it and queues a pull when on. The Companies list, the reader and the company strip draw the toggle beside the affinity buttons, the list filters on it, and the board's reach editor drops its All roles option.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 10:44:41 +02:00
WolfandClaude Fable 5.1 308d2c5eff Say in the Where block that its lines add up
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-29 16:53:46 +02:00
WolfandClaude Opus 5.5 3c19ded014 Ask where a role can be as a list of lines it matches any of
The Where block asked for a required country set and then a one-of set,
in ISO codes. It is now one question, "Where can the role be?", with
countries by name, towns, and Remote within Europe or anywhere, each
line read on its own, and a sentence under it that is the card's.
Other rules move under Advanced, open when the agent has one. The
gates the API stores do not change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 16:45:59 +02:00
Wolf 43f0210b88 Merge branch 'wp5-agents-ui' 2026-09-29 16:22:26 +02:00
WolfandClaude Opus 5.5 0996b03f8f Edit an agent's prompts as rows and its gates as a Where block and rules
The card lists each prompt and says the gates in words. The form edits
prompts as name and text rows, and the gates as a Where block (countries
required, then one of countries, remote or places, and prefer hybrid) over
a row per remaining rule. A gate the Where block cannot say lands in a row,
so a load and a save lose nothing. The gates JSON box stays under Advanced,
read only, as a view of what Save sends.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 16:17:15 +02:00
WolfandClaude Sonnet 5.5 6c63139343 Open the job board form in place of its row, and add Platsbanken to it
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-09-29 16:11:59 +02:00
WolfandClaude Sonnet 471ace703c Switch the extract and summarise stages on the page, over config.yaml
A stored `stage:extract` / `stage:summarise` in the state table overrides
extract.enabled / summarise.enabled; with none, the file applies. One
function, stages.stage_on, decides, and both tasks' finders ask it.
GET/PUT /api/stages and `app stages` show and set it with who would answer;
Runs has a "What the model reads" block, and a search agent's card says when
a stage is off and links to the switch.

Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
2026-09-29 15:54:53 +02:00
Wolf 562fa3ab09 Merge branch 'r2-backend'
# Conflicts:
#	app/storage/schema.py
2026-09-29 15:22:03 +02:00
WolfandClaude Opus 2c4b992c50 Country lookup: every ISO country, the widest unit wins, several European countries are EU
country_of folds with _place_fold (ł, đ, ø, æ map to ASCII; _fold keeps building
company_key unchanged), knows every ISO country by English name and European
ones by their own, and the cities among the 150 most frequent unresolved
places on the live data. Within one location a country beats a US state or
Canadian province, which beats a city. A state code that is also an ISO code
counts as the state only when the line names a US place. Several countries,
all European, are EU; otherwise ''. A code in parentheses is read when no
name matched.

Migration 12 recomputes country from place for roles extract has not read
and whose board sent no country in raw. On the live data: open roles with no
country 2,827 -> 1,183 of 16,841; 1,705 open roles change, 48 from a code.

Co-Authored-By: Claude Opus <noreply@anthropic.com>
2026-09-29 15:06:15 +02:00
WolfandClaude Opus b021838959 Calibrate fit and taste per embedding model instead of min-max per run
scale() maps a cosine to clip((cos - lo) / (hi - lo), 0, 1) with constants
from CALIBRATION in app/config.py, keyed by model and replaceable under
embed.calibration. multilingual-e5-small: fit 0.75..0.88, taste -0.14..0.19
(taste from synthetic votes). An uncalibrated model falls back to min-max
and logs a warning once per run.

The extract and summarise bars default to 0.55 and 0.65, about 300 and 35
roles for the starter agent on the measured data; stored limits are kept.
An agent without an intent is left out of the model-stage scope, and each
score run names such agents in one score.no_intent notice.

Co-Authored-By: Claude Opus <noreply@anthropic.com>
2026-09-29 14:59:34 +02:00
WolfandClaude Opus 5.5 3b209d628a Every way a company gets a board is set_board, and an unreadable host keeps its slug
`app.jobs.sources.set_board` attaches a board to an existing company,
replaces the one it has (closing the old board's open roles) or creates
the company, with row and subscription changed in one transaction by
`Store.set_company_board`. A board that lists zero roles is kept. `add`,
`discover --add`, the seed importer (moved out of app/cli.py) and the new
`POST|DELETE /api/companies/{key}/board` all go through it; a seed re-run
attaches a board to a row that never had one. A company's subscription is
rewritten in place, and detaching hides it.

`companies.ats_slug` (migration 9) keeps the slug of a host the app
cannot read yet, and discovery returns such a host before probing slugs.
The Companies rows get Set board / Change, the host select is rendered
from `plugins.ats.HOSTS`, and a row with nothing found reads "board not
found" and is in the "Not readable yet" filter.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-29 14:04:52 +02:00
Wolf 6779dda888 Merge branch 'gates-any'
# Conflicts:
#	README.md
#	app/storage/store.py
2026-09-28 19:30:27 +02:00
WolfandClaude Fable 5.1 fb83ae5099 Gates reject on evidence only, any gates are one group, remote is read off the location line
A require gate on an empty column gated the role ("country unknown"), and extract, the stage that fills the column, is bounded to the roles that rank, so 2,281 of 15,556 open roles could never come back: every board that writes "Remote", "Hybrid" or "Distributed" as its location. An empty column now neither passes nor fails a gate; the role ranks, extract reads it, the rescore decides.

`any` is a third gate mode: the any gates are one group a role must match one of, so a ranking can say "in Denmark, or remote", which require alone could not. The group is gated only when some member had evidence against it.

`remote_of(place)` fills `remote` from the location line the way `country_of` fills `country`, and the startup backfill does both, since Greenhouse writes "Hybrid" as the location and gives no flag.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 19:30:06 +02:00
WolfandClaude Fable 5.1 c63f348dc9 Merge main: the Runs cleanup meets the queue's own idle text
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 16:24:24 +02:00
WolfandClaude Fable 5.1 3a240e51df Pull pipeline/ from boilerplate a80ad8a: cadence picker, queue badge, label refresh
The schedule cadence is a picker, the add row is behind a button and off
here, a running-jobs chip with Kill and Stop run sits in every header, and
a declared schedule's label is refreshed at startup.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 16:22:46 +02:00
WolfandClaude Fable 5.1 8532e4e739 Runs is the queue's elements and a Problems log; a Kill lands between boards
Run one stage goes: the cascade is the unit of work and app job keeps the
per-stage entry points. The pull button is disabled while a pull runs and
the lede no longer hardcodes the cadence. Messages folds into Runs as
Problems. pull_batch checks for a cancel before every board, one plugin per
target, and both plugins now close their HTTP client.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 16:10:38 +02:00
WolfandClaude Fable 5.1 cebe62ddc9 Extract and summarise bounds are each agent's own limits, set on its form
agents.limits holds extract_top, extract_min, summarise_top and
summarise_min; the scope query reads them per ranked row, and a row saved
before this behaves like a fresh agent. The four global config keys go.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 16:02:06 +02:00
WolfandClaude Fable 5.1 e602eb3388 Drop pruning boards by region: a fix for the US seed, and a wrong one
`app companies prune`, `/api/prune` and the Sources disclosure switched off every board with no open role in a region. It existed because the first seed was 186 US boards; the European seed makes it moot, and it was wrong on its own terms: a board with no European role today (a company between openings, or a fetch that timed out) was switched off for good. A company that hires nowhere near should not be in the list, and a ranking's country gate handles the rest. `EUROPE` in models had no other reader and goes with it.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 15:35:18 +02:00
Wolf 3aee48997c Merge branch 'seed-europe'
# Conflicts:
#	README.md
2026-09-28 15:27:48 +02:00
WolfandClaude Fable 5.1 51d1e67ff9 A European seed of 362 employers, readable or not; discover finds a company's board from its site
The seed was jobhunt-hq's 186 US boards, chosen because they could be read. It is now a hand-picked list of European tech employers, with `board` filled by the new `app.jobs.discover` from each company's own careers site and every board fetched once before it landed: 175 have one, and the rest keep the ATS host their site runs on (Teamtailor 32, Workday 12, SuccessFactors 9, ...) and a careers URL, as rows the app cannot read yet. Companies shows them as "not readable yet" with a link, behind a filter, so the next parser to write is the host that filter shows most.

`app companies discover NAME DOMAIN [--add]` reads the home page, its careers links and the usual paths for a link into a known host, one level down on a careers page, and probes Greenhouse, Lever, Ashby, SmartRecruiters, Recruitee and Personio by slug when the pages link nothing. It is what the LinkedIn flow will call.

Migration 7 adds companies.ats, country and city. The Workable parser now reads the v3 shape its list endpoint actually sends (location object, department list, shortcode and no URL or text); the first populated board showed it.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 15:27:14 +02:00
WolfandClaude Fable 5.1 7db77e83a3 Extract is bounded to the ranking: pull → embed → score → extract → score → summarise
The free stages run first and their score bounds the two model stages.
Extract reads only the best extract.per_agent roles of each agent at
extract.min_score or more, then score runs again so the gates read what it
filled; summarise gets a min_score of its own. The cascade steps by
position, since score is in it twice.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 15:26:58 +02:00
WolfandClaude Fable 5.1 c4f2bcc0c9 Viewing as leads the Roles rail; settings get a rail, agent cards, one Sources section at a time
A search agent is a persona, and every like or pass belongs to the one
being viewed. The rail now opens on Viewing as: a full-width chooser,
the name alone with one agent, a note with none, remembered in the URL
and localStorage. The vote buttons, the reader's affinity control, the
feed, the tag counts and the reader fetch all carry that agent; before,
votes sent none and every one landed on the default agent. Best first
and Newest first are back as the segmented control under Order,
independent of the agent. The rail selects no longer clip descenders:
Chrome ignores line-height on a select, so the fixed box is gone in
favour of padding and a min-height.

Settings render inside a sticky rail (Search agents; Sources with Job
boards, Company boards, Runs, Messages; Account), a strip under the
header on a phone, so Runs is one click away however long the company
list gets. Sources shows one section at a time, chosen by the fragment,
so the old redirects still land. Search agents are cards, newest first:
name, an On/Off switch with its word, the intent in full, the weights,
Edit in place, New agent on top, and a link to Roles as that agent.
Switching one on rescores it.

replace_scores writes nothing for an agent deleted while score was
running, instead of failing the run on the foreign key.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 15:05:55 +02:00
WolfandClaude Fable 5.1 a0772519b3 Per-agent ranking: votes, affinity and a taste term; settings are three sub-tabs
Votes on roles and company affinity move to role_votes and agent_companies,
one row per search agent, so two agents rank the same roles differently. The
score gains taste, the cosine to mean(liked) - mean(passed) of the agent's
votes, as newsdesk ranks articles. The API takes agent on roles, votes and
companies and falls back to the default agent, the enabled one with the
lowest id.

Settings become Search agents (a list again, with New and Delete), Sources
(job boards, company boards and runs with the message log, one section per
plugin) and Account. Old paths answer 301 to their section.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 12:53:41 +02:00
Wolf fe83330c82 Merge branch 'worktree-agent-a8ed2a864305c4381'
# Conflicts:
#	app/web/api.py
2026-09-25 22:03:19 +02:00
WolfandClaude Fable 5.1 55248555e9 Companies and Searches: follow, hide not mute, prune moved, one row style
Companies gets a Follow-a-company form, a combined affinity/on-off filter,
and one .srow-style row per company (name, board or "from searches", open
roles, on/off switch, affinity). The prune-by-region tool moves here from
Searches, folded under the list in a <details>. The lede states the
difference between switching a board off (stops reading it, closes its
roles) and hiding a company (keeps reading it, keeps its roles out of the
list and unscored).

affinityControl becomes three icon toggles (favourite, like, hidden) instead
of four letter buttons with a neutral one; pressing the pressed icon clears
back to neutral. "Hidden" is the word everywhere the UI names affinity -1;
the code keeps mute/hide_muted. CompanyOut carries each company's board
subscription id and on-state, so the Companies page needs only
/api/companies, not a second fetch of /api/sources. Setting a company's
affinity now enqueues a score job, deduped by the queue to one run.

Searches keeps only the search form and list, in the same row style;
company boards and the prune tool left with it, and "Pull now" left for
Pulls (package B3).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-25 22:02:28 +02:00
WolfandClaude Fable 5.1 a5af47349f Pulls: Pull now on top, one stage at a time tucked away
Pull now moves from the Sources page's own button to Pulls, wired the same
way (POST /api/jobs {kind: "pull"}), sitting beside what is running. The
schedule follows, then extract, embed and score move under a "Run one
stage" details -- jobs.js still draws them from /api/jobs/kinds, minus
pull, which gets the dedicated button instead of appearing twice.

Messages' lede drops the file's own vocabulary (a "fix", "cleared yet") for
the reader's: a fortnight, not a job kind or a config key.

Found but not fixed: at 375px the refreshed desk-schedules still squeezes
its name and cadence columns to a sliver, because kind/next/last size to
their untruncated content instead of the width their own ellipsis implies.
No page-level horizontal scroll comes of it, so overflow-x: auto stays as
the safety net, with a comment pointing at the cause. The fix belongs in
../boilerplate, ahead of the next refresh -- out of reach from this
worktree.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-25 21:52:31 +02:00
WolfandClaude Opus 5.5 7d31cca394 Two tabs and a cog: settings shell, one ranking, a script per page, the phone frame
The top bar is Roles and Applications plus health's cog. Behind the cog,
/settings/{ranking,searches,companies,pulls,messages,account} share one row
of sub-tabs, an underlined row on a desktop and pills on a phone. The old
paths answer 301 with their query string.

Ranking edits the first enabled agent, or creates one, with the intent,
the weights and the gates under Advanced. The order menu on Roles reads
Newest and Best match with one enabled agent, and names them with several.
config.yaml keeps the Copenhagen starter; the other two are commented
examples in config.example.yaml.

roles.js is split into roles.js, applications.js, ranking.js and
companies.js; count, cell, debounce, the company list and the affinity
control live once in app.js. app.css gets the phone frame after health and
newsdesk: one-row bar, edge-to-edge panels, 44px targets and 16px fields on
a coarse pointer, hover only where there is one, safe areas. The app is
installable from a manifest and roledesk-coloured icons. Every lede touched
is written for the person using the app.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-25 21:29:06 +02:00