Places are ordered in tiers off the agent's gates (the any group, then the require scope, then the rest), and within a tier by the home the any group gives, since the gazetteer holds no coordinates. GET /api/roles and /api/roles/{uid} carry place_texts, lead_place and lead_url for the roles served; the gates and the dupes rule are unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The CV is cut into chunks inside e5's window, embedded like a prompt and
cached per agent under a hash of the model, chunking and text. A role's
cv_fit (scores.cv_fit, migration 31) is its best chunk cosine, scaled with
its own calibration band: fit's clipped 88 of agent 2's ungated roles to 1.
It is no term of the Agent match score. judge_cv_top (default 50) sits
beside judge_top and judge_min on the agents page and card.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
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>
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>