77 Commits
Author SHA1 Message Date
WolfandClaude Fable 5.1 1913101061 Drop Advanced › Other rules from the agent form, so an agent's gates are the fetch gate's four parts: a stored gate the parts cannot say is named in a note under the fetch gate and sent back unchanged on Save, and the card still says it in words
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-06 14:33:34 +02:00
WolfandClaude Fable 5.1 8c3c51dd9f With an agent named, the rail's tag, company and place counts, Remote included, cover the roles that agent's feed shows, past its fetch gate; and the affinity note names the order What I'm looking for.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-05 09:35:32 +02:00
WolfandClaude Opus 5.5 1f444aa077 Merge the ADR follow-up in the front end: All locations, the four-part fetch gate and analytics filter on the form, the order labels, no hidden-companies filter, judge numbers of 10 (wp-adr-ui)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 21:41:02 +02:00
WolfandClaude Opus 5.5 6d82287402 Bring the Python side to the ADR: the judge scores 0 to 10 with the cap at 4 and migration 33 clears every judgement, summarise reads the top 30 of the want and the match order, a hidden company's roles are never in the feed, and the company switch is called All locations.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 21:40:32 +02:00
WolfandClaude Sonnet 5.5 b6e27fcb26 Split the agent form's fetch gate into world, location, role exclusion and role fetch, and name the analytics filter and the feed score weights
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-04 21:33:31 +02:00
WolfandClaude Sonnet 5.5 61aadff681 Rebuild the agent form as the fetch gate, the feed order, the cut and summarise, and name fetch text and the overrides as built
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-04 15:27:03 +02:00
WolfandClaude Opus 5.5 8b6c6d5ac3 Test migration 32, the cut, saved filters and the override rescore, and bring the READMEs and config comments to fetch text and the cut
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 15:16:38 +02:00
WolfandClaude Opus 5.5 617356e60c Rank by the cut: fetch gate overrides in scoring, the cut per agent, stages read the cut, fetch text renamed from enrich, the feed kept to the fetch gate, and migration 32
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 15:11:43 +02:00
WolfandClaude Opus 5.5 fb24c8e4c9 Lead a role in several cities with the one nearest the viewing agent, in the row, the reader and the posting link
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>
2026-10-04 08:15:26 +02:00
WolfandClaude Opus 5.5 c23594507a Score each role's closeness to the agent's CV, let the judge also read the 50 closest the score leaves out, and order CV match's unjudged roles by it
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>
2026-10-03 23:35:21 +02:00
WolfandClaude Sonnet 5.5 ee8e450640 Summarise every saved or liked role whatever its rank, queue it at once on save or like, and shorten the order labels to Agent match, CV match and Newest so they fit one line
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 23:14:12 +02:00
WolfandClaude Sonnet 5.5 585c332d74 Make the three CV match weights a per-agent setting, applied when a role is served
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>
2026-10-03 22:25:44 +02:00
WolfandClaude Opus 5.5 4fc474c437 Give an agent a CV, languages, avoid and must texts, and read a posting's languages with a level and its deadline (migration 28)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-03 21:54:16 +02:00
WolfandClaude Sonnet 5.5 6e6e655203 Wire freehire, Jobnet and Akademikernes Jobbank into the CLI, the Sources form, dupes and the docs
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>
2026-10-03 12:24:34 +02:00
Wolf e5572cab9d Merge the remote area: remote tokens, role_remote, remote_from, model wins for remote (wp-remote-a)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	app/models.py
2026-09-30 16:21:57 +02:00
WolfandClaude Fable 5.1 0ad47605fd Expect limits, board_open and the full reader declaration in the exact-row tests
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-30 16:03:48 +02:00
WolfandClaude Opus 5.5 2a0f7fe0c3 Test the remote area with the live boards' place texts
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 16:00:06 +02:00
WolfandClaude Fable 5.1 0e268f3f3c Compare the full board target in Replace board
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-30 15:44:32 +02:00
WolfandClaude Opus 5.5 8c66aeb445 Merge board size set once, Recheck, and the Companies line naming what a site does not know (wp-a-size)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:45:27 +02:00
WolfandClaude Opus 5.5 6085017943 Recheck a board's size from the Companies row, the route and app companies size
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>
2026-09-30 13:44:54 +02:00
WolfandClaude Opus 5.5 a0882e9659 Size a board once with board_size, before a pull reads it with no size, and name what a site's ids leave out
set_board sizes a board from page 1's total, or reads to the end on a host that states none, instead of reading it whole up to page 100. A pull no longer rewrites ats:size; a board with none is handed the agents' reach marked unsized and is sized in its batch first, or by its whole read on a host that cannot narrow the reach. reach.sizes drops the open-role fallback. The Companies line names countries a Workday or Oracle site does not list and a missing remote option.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:43:52 +02:00
WolfandClaude Opus 5.5 d168d9eb6c Add migration 26, roles.posting_url, kept across pulls and carried on the row and its copies
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:26:20 +02:00
WolfandClaude Opus 5.5 d529f6c0ce Merge the seniority range filter: From, To and Track in the rail (wp-sen-b-range)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:14:45 +02:00
WolfandClaude Opus 5.5 06ff9f549b List unlinked places and unmapped words under Sources, fix them in code with the unmapped skill
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>
2026-09-30 13:06:22 +02:00
WolfandClaude Opus 5.5 4e390d97ca Filter seniority by a range of rungs and a track: level_from, level_to, track; From, To and Track in the rail (WP B)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 13:03:31 +02:00
WolfandClaude Opus 5.5 e52857dea5 Split the All tag into two company overrides: All countries and All roles (WP L)
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>
2026-09-30 12:50:45 +02:00
WolfandClaude Opus 5.5 d04ceae7e0 Prep stage: host words stored raw, mapped centrally in app/prep after every pull
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>
2026-09-30 11:19:22 +02:00
WolfandClaude Opus 5.5 5d5b7e7d3f Tag a company All roles to read its big boards with the agents' wide reach; favourite scores only
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>
2026-09-30 10:44:41 +02:00
WolfandClaude Opus 5.5 ca80219bbb Merge branch 'wp-f-reach'
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 10:04:26 +02:00
WolfandClaude Opus 5.5 dafca5435e Show and set each board's reach on the Companies list, list the readers' declarations on Sources, and document filtering at the source
A company row says what a pull asks its board for; its editor sets the board's own reach (the agents', all roles, or countries and remote) through /api/sources/{id}/reach. /api/readers lists each reader's listing, text, filters, places and robots decision, folded under the Follow form.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 10:03:41 +02:00
WolfandClaude Opus 5.5 9172b2da72 Companies as symbols: company_aliases, merge, duplicates, empty enrichment columns (migration 20)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 09:45:43 +02:00
WolfandClaude Opus 5.5 545c932f7b Store copies of one posting as roles.dup_of and leave them out of the feed, the counts and the model stages
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>
2026-09-29 23:09:20 +02:00
WolfandClaude a91b4e99e0 Filter the feed by company keys, place tokens and seniority, and suggest companies and places
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>
2026-09-29 22:17:12 +02:00
Wolf 1a2689e08d Merge branch 'main' into wp1-byhand-api
# Conflicts:
#	app/models.py
#	app/storage/schema.py
#	app/storage/store.py
#	app/web/api.py
#	tests/test_storage.py
#	tests/test_web.py
2026-09-29 19:25:42 +02:00
WolfandClaude Sonnet 5.5 28afc334c3 Add, edit, check and delete a company by hand through the API, and show the by-hand fields in the list
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-09-29 17:02:19 +02:00
WolfandClaude Sonnet 5.5 7dcb2c1705 Add a Watchlist tab for the companies the app cannot read a board of
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>
2026-09-29 16:56:16 +02:00
WolfandClaude Fable 5.1 0458c9c172 Take a Platsbanken region in the API and the CLI, and trust its and Teamtailor's posted date
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-29 16:23:19 +02:00
Wolf 7939b99a5c Merge branch 'wp4-prompts' 2026-09-29 16:22:26 +02:00
WolfandClaude Opus 5.5 4e3c3f130e Give a search agent several prompts and score a role by its best one
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>
2026-09-29 16:19:57 +02:00
WolfandClaude Fable 5.1 aabf2b4f1b Name an unreadable host in the two tests that used Teamtailor for one
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-29 16:15:55 +02:00
WolfandClaude Fable 5.1 92466e2cd4 Drop the retry around the queue's dedup race, fixed upstream
`_score_after_change` tried three times because `Jobs.enqueue` could re-raise an IntegrityError when the live job finished between its insert and its lookup. The queue now does both in one BEGIN IMMEDIATE transaction (boilerplate a1c6f0d), so the workaround and its test go.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-29 16:02:58 +02:00
Wolf a629eda8de Merge branch 'r2-web'
# Conflicts:
#	app/static/roles.js
#	app/web/api.py
#	tests/test_web.py
2026-09-29 15:31:35 +02:00
Wolf 562fa3ab09 Merge branch 'r2-backend'
# Conflicts:
#	app/storage/schema.py
2026-09-29 15:22:03 +02:00
WolfandClaude Sonnet 91596300e1 Serve a row projection from GET /api/roles instead of the whole role
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>
2026-09-29 15:22:00 +02:00
WolfandClaude Opus b2c8c08f7f Judge an employer known only from a search; the Companies list says "from job boards"
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>
2026-09-29 15:19:55 +02:00
WolfandClaude Sonnet e6be593542 Ask before a destructive board or search switch; queue a pull after a reopening one
Switching a company's board or a job board search off, replacing a
company's board and detaching one all close open roles in a tap; each
now asks first, naming the count (a replace also names the old and the
new board), the same as removing a search and deleting an agent
already do.

Switching a target back on, following a board, setting a board and
saving a search used to show nothing until the schedule's next pull,
up to six hours later. Each now queues a pull job right in the API
route, so the CLI and any other caller of the same endpoint behave
like the page; the queued pull's own refusal while one is already
running is not surfaced as an error.

Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
2026-09-29 15:18:16 +02:00
WolfandClaude Opus 91d15fcc7d A change made while score runs gets one follow-up score, and the page waits on it
score is solo, so a request during a run was deduped into the running job,
which had already read the old state. _score_after_change returns a queued
score when one has not started, else enqueues a plain score and, if that
dedupes to a running job, one follow-up with depends_on it, after="done" and
dedup_key score:after:<id>. POST /api/score answers with that job and
agents.js waits on it; the affinity route answers with score_job.

The flaky affinity test was pipeline's race, not the app's: Jobs.enqueue
re-raises the UNIQUE IntegrityError when the live job it collided with
finishes before the SELECT that should hand it back. The app retries.

Co-Authored-By: Claude Opus <noreply@anthropic.com>
2026-09-29 15:16:23 +02:00
Wolf bbb7474cef Merge branch 'r2-salary' 2026-09-29 15:09:19 +02:00
WolfandClaude Sonnet fa4e1a657f Keep a board's stated pay as salary_text, even when it does not normalise
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>
2026-09-29 15:08:45 +02:00
WolfandClaude Opus b021838959 Calibrate fit and taste per embedding model instead of min-max per run
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>
2026-09-29 14:59:34 +02:00