The OpenAI and Mistral roles agent 2 let through are not a gazetteer mix-up:
Montréal resolves to Canada and San Francisco to the US. Each is the kept
role of a posting folded with a copy in Dublin, Munich or Paris, and the
gate reads every place of a kept role. Tests hold both, decisions.md says so.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
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>
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>
The readers flattened a posting's HTML into one line with strip_html, so
sections and bullets ran together. _shared.html_text gives a line per
paragraph, '• ' before a list item and '## ' before a heading; every
reader's description goes through it, sections read per role get their
own headings, and the reader pane draws the lines as h3, ul and p.
Excerpts leave the marks out.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/api/suggest/places offers "Remote" (remote:any) first for "remote", counted in the scope of the agent asked for or the default agent, then the countries, then "Remote · <place>".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
remote_where is a list of names, [] when not stated. Remote is remote with a regular office week and hybrid with set office days each week.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The area is the model's names, else the parts of the place texts that say remote, else the resolved places as their countries. VERSION 3 maps every open role again. run_roles maps the roles extract answered. "Remote Sensing" in a title is no remote work.
Co-Authored-By: Claude Opus 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>
remote:country:DK is a remote role whose area overlaps Denmark: what lies in it, what it lies in, Anywhere. remote:anywhere is Anywhere alone and remote:any the viewing agent's scope. Anywhere is a continent outside the tree with no alias. Remote parts of a line are no town, and the suggestions offer the remote tokens after the countries.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds the search providers' PARAMS, clean_params and company, and a test
that the example READS is workday.py's.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Ten entries were shadowed by their modules. A test now holds that no entry
names a reader, which replaces the per-host checks.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A missing fixture fails with the path to add. Detail fixtures are named
<name>-detail*, the rows of a paged read state a total as complete says,
and a host that states words has a prep table for them.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Every reader declares, so undeclared(), the scope() fallback, robots_page and
ROBOTS_ANY_CASE go. A search provider needs PARAMS and clean_params, a row may
carry company, places gains none. Each robots record names the paths the
reader requests, from robots.txt read again on 2026-09-30. Platsbanken states
remote, HR Manager states no place.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
State that the 76 is the seed's count, name the survey files that do not exist, make WP9 own _runner.py because detail cannot fill a title until DETAIL_FIELDS has it, and make it wait for plan-remote's WP-A and the review's R1, which own the same files.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
State which hosts the survey covers and which it leaves out, fix the Workday and Oracle facet names, the All countries versus All roles sentence and the places-in-reach claim, mark the Workable, Teamtailor and Jibe query rows as not built, and reword the plan voice and first person.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Update the stale counts, state which boilerplate copies lag and by what, record HR Manager as attached against its robots record, add Ashby to the empty-slug item, the SmartRecruiters case question and the seed lag, and add a section for what the review of 2026-09-30 does not build.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Each older paragraph that a later decision contradicts (cascade, Jobindex completeness and link-out, host counts, HR Manager and the three Workday companies, summaries, seniority order, trusted dates, tabs, the 175 count) gets one sentence naming what replaced it. The Jobindex robots record names sort=. Em-dashes and a role called a job are reworded.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The seed has 286 boards, not 175. The pull now maps and enriches; Platsbanken is a third provider; Sources has an Unmapped section; the company row shows size, reach and the two overrides; Fetch follows the Se jobbet link; the CLI has size, agents, prep, seniority and dupes.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Add a Flow section with the state keys, describe per-role text as read by enrich after scoring, move SmartRecruiters and Workable to list-then-each-role, refresh the Overview counts, fix the shared rules, the per-host rows, the search providers and the Watchlist table, and point at _runner.py and READS for what they own instead of restating them.
Co-Authored-By: Claude Fable 5.1 <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>
POST /api/sources/{id}/size sizes the board again, keeps the day and queues a pull; /api/companies returns size and size_checked, and the row shows "999 roles · checked 30 Sep" with Recheck beside Change. app companies size <key> does the same from the CLI, and --missing sizes every board without a size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>