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>
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>
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>
roles.remote_model, roles.remote_where_model and role_remote, with a stored remote no host word gives kept as the host's word. The remote tokens filter over role_remote, remote_from and a require gate on country read a remote role through its area, extract waits while remote_where_model is NULL and writes the model's remote outright, and rows carry remote_where.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
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>
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>
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>
The search providers stop mapping remote_word themselves (R2), so prep reads
the same words: in any role's place line after remote_of, and in the title of
a role from a search.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
upsert_role stores the host's own words (roles.*_host), the place texts
unresolved when they change, and the company key unresolved on insert, and
marks the role prep_due. app.prep maps seniority, employment, remote and
country through the host tables in app/prep/hosts, resolves places and
company aliases, lists unknown words in `unmapped`, remaps every open role
when the tables' fingerprint changes, and runs rebuild_dupes, which moves
out of the pull's settle. Migration 22 adds the columns and the table and
fills the host words from raw. Cascade: pull, prep, embed, score, enrich,
prep, embed, score, extract, score, summarise. `app prep [unmapped]
[--remap]`, /api/prep/unmapped and a fold on the Sources page.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
The pull reads listings only. `enrich` (app/jobs/enrich.py) takes the open
roles without text that an enabled agent ranks ungated in its best
`enrich.top` at `enrich.min_score` or above, best score first, on boards
whose reader has `detail`, within `enrich.per_board` and `enrich.per_run`,
one batch per board. `plugins.ats.read_board_details` reads them and keeps
the per-board state; a read that gave no text is read again after
`enrich.retry_days` (finding 18). Filled roles are upserted, which drops
their vectors, and embed and score follow; `cascade.step` passes over both
when nothing was filled.
The pull cascade is pull, embed, score, enrich, embed, score, extract, score,
summarise. Saving an agent and changing a company's affinity queue the
`enrich` job (enrich, embed, score) behind their rescore; a vote does not.
The stage has a switch, `stage:enrich`, over `enrich.enabled`.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The reader shows every place, each linked to its copy, and the teaser marked as a short description when there is no text.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Migration 19 adds places, place_aliases, place_includes (seeded from the
dictionaries in app/models.py and app/places.py, Europe as a continent over
the European countries) and role_places, one row per place of a role,
resolved by app.places.Gazetteer, NULL when unknown. upsert_role writes them
from raw["places"], else the place line cut at ";"; the migration builds them
from each role's place column.
The Place filter and the country and place gates are joins over the tree:
country:DK is any place under Denmark, region:skane any town in Skane, a
country gate is met by any place in its countries, and the EU fallback of
the word matcher is no longer used. A place: token the gazetteer does not
know still matches whole words. Store gains gazetteer, role_places,
unresolved_places, add_place_alias, add_place and relink_places.
roles.teaser is kept-filled and embedded while there is no description; a
vector is dropped when a better text arrives. seniority_model, _stated and
_title sit behind roles.seniority, which stays the first filled of them.
TRUSTED_POSTED_HOSTS gives way to trusted_posted(host), which reads
READS.fields.posted and falls back to the old set for undeclared readers.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Migration 18 adds roles.dup_of with a partial index and runs the first rebuild. Store.rebuild_dupes feeds app.dupes.assign the open roles of every (company_key, title_key) with more than one, rewrites dup_of where it changed, clears it on closed roles, and hands read_at and votes to a changed group's kept role. The pull's settle and `app dupes` run it. RoleRow.copies counts a row's open copies; Role.copies lists them and Role.dup_of names a copy's kept role.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A role listed before its page was read kept a title-only vector, and the listing's place replaced the page's on every later pull.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Migration 17 adds roles.place_fold and fills seniority from the title where extract has not read the role. Every connection registers place_match, so the Place filter and the place gate match whole folded words: Lund no longer finds Billund. GET /api/roles takes company_keys, places, seniority, seniority_unknown and pay_unknown; new routes suggest companies and places, label place tokens and count the seniority and pay facets.
Co-Authored-By: Claude <noreply@anthropic.com>
The search field on Roles takes the phone top bar while it is typed in,
since a third tab left it a few letters wide.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Rate each one Yes or No apart from affinity, open its careers page with the
time noted, and set a missing or wrong link in the row. Migration 15 adds
companies.watch and careers_opened_at.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Migration 14 moves each non-empty agents.intent into agent_prompts as one
prompt named after the agent, with its cached vector, and drops the three
intent columns. A role's fit is the maximum over the agent's prompts of the
calibrated cosine, and scores.prompt names the prompt that won. The agents
API takes prompts and still takes intent; the role endpoint serves the
agent's score and prompt.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The feed only ever shows a title, a few badges and a short excerpt,
but the list endpoint answered with every role's full row --
description, feed_text, raw and article_text included, about 5.5 KB
a role -- so a 1000-row restore was several megabytes of text a phone
never renders.
Store.roles_page selects only the fields a row draws (RoleRow), with
excerpt built server-side off a SUBSTR of summary or description, so
the big columns never cross into the response. The reader is
unaffected: it already fetched the whole role by uid when it opened
one; the reader pane's own reliance on the list row carrying the body
is removed too, so it no longer flashes a wrong "no description"
before that fetch lands.
Measured on a copy of the live database: a 60-row page went from
392 KiB to 39 KiB, and a 1000-row restore from 6.6 MB to 631 KiB.
Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
Store.set_affinity creates a minimal company row (key, and the name its roles
give most often) for a key with roles and no row, so a Jobindex or Adzuna
employer can be hidden or liked; the reader draws the control for any role
with a company_key and reloads the company list after the first change.
/api/companies derives from_search: no ats subscription (detached included)
and no ats, careers_url or domain. companies.js labels it "from job boards"
and keeps it out of "Not readable yet".
Co-Authored-By: Claude Opus <noreply@anthropic.com>
Every ats parser now writes one human-readable pay line whether or not it
converts to yearly salary_min/salary_max/currency: hourly and daily rates,
Greenhouse's several pay zones, and a range with no currency all survive as
text instead of being dropped outright. Stored in roles.salary_text
(migration 12), replaced whole on every pull like title, so a board that
stops stating pay clears it rather than leaving a stale line. salary_state
is derived, not stored ('normalised', 'stated', or ''), and is what the
feed's new Pay filter and badge read; gates and scoring are unchanged, still
reading only the normalised columns.
Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
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>
Part A: Ashby (?includeCompensation=true), Greenhouse (pay_transparency=true,
already free on the list request), Lever (salaryRange), Recruitee (salary)
and Personio (salaryInformation) all give structured pay; Workable and
SmartRecruiters do not (checked live). Every host converts to a yearly
salary_min/salary_max/currency, multiplying a monthly figure by 12 and
skipping an hourly or daily one rather than annualising a number nobody
stated. A range with no currency is ignored, and Greenhouse's own multi-zone
ranges are skipped outright since nothing says which zone the role is at.
Part B: classify() matched substrings, so " it" matched inside "Italy",
filing European sales roles as engineering; it now matches on word
boundaries (full boundary for the handful of short tokens that are
themselves the start of an unrelated word, prefix matching kept for the
stems). Title is checked before department (a hand-checked sample found
title-first right about twice as often), nothing matching returns '' rather
than "other", and a modest set of German/Dutch/Danish/Norwegian/Swedish/
French keywords covers the seed's other languages.
function is not a board field, so it gets the opposite rule from every
other raw column: extract's answer overwrites the classifier's guess
outright, and once extracted_at is set no later pull may put the guess
back. Migration 9 recomputes function for every not-yet-extracted role from
its stored title and department.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
recency and the newest feed both counted from first_seen, when the app
itself first stored a role, so a newly added board's whole backlog scored
as freshly posted for two weeks: 10,223 of 15,415 board roles were posted
more than 30 days before they were first seen (average gap in days: Ashby
78, Greenhouse 143, Lever 226, Personio 333).
Add roles.posted_at (migration 9): the earlier of first_seen and a trusted
host's published_at, where TRUSTED_POSTED_HOSTS (app/models.py) records
which of the ats and search hosts report a creation date rather than one
that moves on an edit, checked against live boards and the live database.
A future or pre-2015 date is not trusted either. upsert_role sets it on
insert and keeps the earliest on update, so an edit on the board can only
move it earlier, never later. recency, the feed's newest order, the "new
since" days filter and _top_scope's tie-break now read posted_at;
first_seen is unchanged and still what the UI shows as when the app found
a role. The row's age in roles.js now shows the posted date instead.
A partial index (posted_at DESC, uid) WHERE closed_at IS NULL serves the
newest feed; sqlite3's bundled build has no STAT4, so its planner
otherwise sorts every open role instead of using it, measured 30x slower
on the live database, so Store.roles() forces it for that query shape.
Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
A second pull (schedule, Run button, `app job pull` in another process) could
start while one was fetching and overwrite the stored run marker, so the first
run's boards failed their stamp check or a settle closed on the other run's id
lists. `claim_run` sets `pull:run` in one conditional statement, only while it
equals `pull:settled` or is older than an hour; a refused `pull` job queues no
stage and says so in its result and a notice, and the CLI exits 1. Batches
carry the marker in their payload, the plugins stamp with it, and the settle
reads it off its own batches' payloads before releasing the run.
Co-Authored-By: Claude Opus <noreply@anthropic.com>
`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>
Workable and SmartRecruiters page their lists, and both parsers read page one
only, so the settle closed every role past it (Delivery Hero: 980 stated, 100
open). `_paged` follows nextPage and offset, and the plugin stamps
`ats:complete` only when the distinct ids read equal the stated total; a 429
after page one keeps what was read and closes nothing. Adzuna completes on its
`count`, Jobindex counts raw items and raises on an answer with no channel.
A board whose fetch raises is recorded under `ats:failing:<target>` with the
first failure's time and the latest reason; after STALE_DAYS the settle closes
its roles, and its next answer reopens them. `/api/companies`, the Companies
list and `app companies check` show it.
Co-Authored-By: Claude Opus <noreply@anthropic.com>