Commit Graph
12 Commits
Author SHA1 Message Date
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 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
Wolf 43773efc53 Merge branch 'worktree-agent-a3bd292551395dda0'
# Conflicts:
#	app/storage/schema.py
2026-09-29 14:16:35 +02:00
WolfandClaude Sonnet 75eca1c914 Date a role by posted_at, not just first_seen
recency and the newest feed both counted from first_seen, when the app
itself first stored a role, so a newly added board's whole backlog scored
as freshly posted for two weeks: 10,223 of 15,415 board roles were posted
more than 30 days before they were first seen (average gap in days: Ashby
78, Greenhouse 143, Lever 226, Personio 333).

Add roles.posted_at (migration 9): the earlier of first_seen and a trusted
host's published_at, where TRUSTED_POSTED_HOSTS (app/models.py) records
which of the ats and search hosts report a creation date rather than one
that moves on an edit, checked against live boards and the live database.
A future or pre-2015 date is not trusted either. upsert_role sets it on
insert and keeps the earliest on update, so an edit on the board can only
move it earlier, never later. recency, the feed's newest order, the "new
since" days filter and _top_scope's tie-break now read posted_at;
first_seen is unchanged and still what the UI shows as when the app found
a role. The row's age in roles.js now shows the posted date instead.

A partial index (posted_at DESC, uid) WHERE closed_at IS NULL serves the
newest feed; sqlite3's bundled build has no STAT4, so its planner
otherwise sorts every open role instead of using it, measured 30x slower
on the live database, so Store.roles() forces it for that query shape.

Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
2026-09-29 14:13:06 +02:00
WolfandClaude Sonnet b560cdce2a Switch the embed model to multilingual-e5-small for the European corpus
Measured on the live roles against the "Copenhagen engineering" agent's
intent: the English-only all-MiniLM-L6-v2 separates engineering from
non-engineering roles with an AUC of 0.68 overall but only 0.74 restricted
to Danish-country roles (a Danish engineering role beats the rest's
non-engineering median only 68% of the time). multilingual-e5-small reaches
0.70 overall and 1.00 on Danish-country roles, for about 3x the CPU time.
paraphrase-multilingual-MiniLM-L12-v2 measured worse than the English-only
baseline (AUC 0.60) and was dropped.

e5 needs "query: "/"passage: " prefixes; app/jobs/embed.py adds them by
matching the model name so a model change can't leave a stale prefix
setting behind. Added tests for the prefixing and for the two invariants
the model change relies on: embed drops the old model's vectors before
re-embedding, and an agent's cached intent vector is keyed by model so a
model change is a cache miss, never a stale-dimension read.

Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
2026-09-29 13:59:47 +02:00
Wolf 6779dda888 Merge branch 'gates-any'
# Conflicts:
#	README.md
#	app/storage/store.py
2026-09-28 19:30:27 +02:00
WolfandClaude Fable 5.1 fb83ae5099 Gates reject on evidence only, any gates are one group, remote is read off the location line
A require gate on an empty column gated the role ("country unknown"), and extract, the stage that fills the column, is bounded to the roles that rank, so 2,281 of 15,556 open roles could never come back: every board that writes "Remote", "Hybrid" or "Distributed" as its location. An empty column now neither passes nor fails a gate; the role ranks, extract reads it, the rescore decides.

`any` is a third gate mode: the any gates are one group a role must match one of, so a ranking can say "in Denmark, or remote", which require alone could not. The group is gated only when some member had evidence against it.

`remote_of(place)` fills `remote` from the location line the way `country_of` fills `country`, and the startup backfill does both, since Greenhouse writes "Hybrid" as the location and gives no flag.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 19:30:06 +02:00
WolfandClaude Fable 5.1 cebe62ddc9 Extract and summarise bounds are each agent's own limits, set on its form
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>
2026-09-28 16:02:06 +02:00
WolfandClaude Fable 5.1 a0772519b3 Per-agent ranking: votes, affinity and a taste term; settings are three sub-tabs
Votes on roles and company affinity move to role_votes and agent_companies,
one row per search agent, so two agents rank the same roles differently. The
score gains taste, the cosine to mean(liked) - mean(passed) of the agent's
votes, as newsdesk ranks articles. The API takes agent on roles, votes and
companies and falls back to the default agent, the enabled one with the
lowest id.

Settings become Search agents (a list again, with New and Delete), Sources
(job boards, company boards and runs with the message log, one section per
plugin) and Account. Old paths answer 301 to their section.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-28 12:53:41 +02:00
WolfandClaude Opus 5.5 8b246c3035 Scale fit across each agent's run, and lower the starter prefer weights
With fit as (cos + 1) / 2 the real run spanned about 0.55 to 0.79, so a
prefer gate at weight 0.2 moved a score more than the whole spread of fit.
fit is now the cosine min-max scaled across the roles an agent scores in
that run: the closest is 1, the farthest 0, a single role 1, and a role a
require gate rules out stays out of the range. The starter agents' prefer
weights drop to 0.05, enough to break a tie. A regression test pins the
case: two close cosines that the old mapping let a 0.05 gate reorder.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 12:51:08 +02:00
WolfandClaude Opus 5.5 59a301c351 Wire the app like the boilerplate: door, queue, schedules, eight tabs
app/main.py assembles it in the boilerplate's order, auth.connect first,
then the queue with the scheduler and the pages. TABS is Roles,
Applications, Agents, Companies, Jobs, Schedules, Messages and Account:
the alpha page's three views become templates on the boilerplate's
base.html, driven by static/roles.js (the old app.js) through api() and
toasts.js, over the unchanged JSON routes. Companies lists every board with
its open roles and the affinity control. A 422 is one sentence, so a toast
never reads [object Object].

Config takes the boilerplate's shape: APP_CONFIG or config.yaml, a missing
file is the defaults, an unknown key is an error. roles.yaml is gone;
config.yaml is the committed default and carries the starter agents.

pull is now a job that asks for the pull cascade, because a schedule
enqueues a job kind; its default schedule, every 6h, is declared beside it
in app/jobs/cascade.py. pull_batch's targets are keyword-only so the Jobs
tab offers no batch button. `app worker` is the boilerplate's; `app job`
still drains a queue of its own and fires no schedules.

test_coupling holds pipeline, auth and desk apart (desk may import
pipeline) and plugins to desk; test_architecture keeps app's layers, now
with main.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 12:48:12 +02:00
WolfandClaude Opus 5.5 7a63311714 Rename the package roledesk to app
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>
2026-09-23 12:30:10 +02:00