from_title matches a title twice, for the highest people level and the
highest individual grade. A people level wins on its own rung; a grade
above that rung lifts it one rung (Principal Engineering Manager is a
senior manager). Senior Staff is principal, Senior Principal, Distinguished
and Technical Fellow are distinguished; Associate Director, AVP and Senior
Manager are senior managers. lead is now a team lead only (Team Lead, Shift
Lead, Supervisor, Teamleiter); Tech Lead, Lead X and X Lead(er) are staff.
A slash names two levels, so Senior/Staff is staff.
- Jobylon "lead" maps to staff; Recruitee maps student_college, manager,
senior_manager and executive.
- extract's prompt describes the ladder and its two tracks; enum from LEVELS.
- prep VERSION 2, so the next prep maps every open role again.
- Migration 25 clears seniority_model where it is staff, lead, manager or
director, so extract reads those roles again, and sets roles.seniority to
the first filled of model, stated and title.
- The coverage test of tests/test_seniority.py passes; its xfail is gone.
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>
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>
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>
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>
The boilerplate's rule: the deploy kit's Dockerfile, the APP_CONFIG,
APP_PASSWORD and APP_DATA variables and its commands all assume a package
called app, so a project renames its display title and nothing else. The
console script is `app`, and the launch entry runs `uv run app serve --port
8790`. The domain noun stays `role`.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
roledesk job extract reads open, unanswered roles 20 to a call and fills
place, country, remote, seniority, salary, currency, function, permit and
languages, only into columns the board left empty. Schema v2 adds
roles.permit, roles.languages and roles.extract_tries. Off by default.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>