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>
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>