Record the world read, the remote mark, the one-country fold, the judge's languages and the end of must-haves in decisions.md, and cut open.md to what is still open
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
1 parent
c6730062fd
commit
8b875b377b
2 files changed
+15
-37
No files matched your search
+7
-1
@@ -16,7 +16,7 @@ What was decided for roledesk and the reason for each. The target design is the
|
||||
|
||||
**A group is rows that all match each other, never a chain.** A row with no place matches Belgium and the Netherlands, and joining on one match merged both on the live data. Rows are taken sharpest first (a town, then only a country, then neither) and join a group only when they match every member.
|
||||
|
||||
**One posting per place is folded too, on every host.** A host that lists one job once per office gives rows of the same company and title whose towns never meet; `dupes.fold` merges those of one host when their texts share at least `SAME_TEXT` (30%) of their words, and the kept role keeps each copy's place and link. It applies to every host, not only to readers that declare `places="copies"`, because most such rows came from hosts that do not declare it. A remote listing and an office listing stay two roles: the kept role takes a copy's places and not its remote, and the fetch gate reads a remote role by its area, so a remote listing folded behind an office elsewhere was rejected with it, and an office listing behind a remote role elsewhere likewise.
|
||||
**One posting per place is folded too, on every host.** A host that lists one job once per office gives rows of the same company and title whose towns never meet; `dupes.fold` merges those of one host when their texts share at least `SAME_TEXT` (30%) of their words, and the kept role keeps each copy's place and link. It applies to every host, not only to readers that declare `places="copies"`, because most such rows came from hosts that do not declare it. It keeps to one country, as ADR 1.4 has it, since the same rule across countries merged different openings whose texts happened to be alike (a federal sales role in the US behind one in Australia); a job posted once per country is then one role per country, which costs a few rows for a pan-European posting and hides nothing. A remote listing and an office listing stay two roles: the kept role takes a copy's places and not its remote, and the fetch gate reads a remote role by its area, so a remote listing folded behind an office elsewhere was rejected with it, and an office listing behind a remote role elsewhere likewise.
|
||||
|
||||
**A copy is stored as `roles.dup_of` and rebuilt from scratch after every pull.** Every reader of open roles adds `dup_of IS NULL`, which keeps `idx_roles_posted` usable where a window function over the filtered rows would scan them all. Where a group changed, the kept role takes the earliest `read_at` and each agent's latest vote from its copies; an unchanged group is left alone, so marking a role unread again sticks. The per-board counts on Sources still count copies, since they report what a board holds.
|
||||
|
||||
@@ -70,6 +70,10 @@ What was decided for roledesk and the reason for each. The target design is the
|
||||
|
||||
**A read that stalls is incomplete, and a sweep's cursor may be a pair.** A reader that sees the host send a page again hands it over empty with a cursor, and the runner ends the read incomplete; a cursor of None there read as the last page, and on a host that states no total as a complete read that closed what the pages had not listed. With a stated total a page of ids already read is not a stall, since a resumed sweep starts on one when the list grew at the top. A cursor is kept across pulls when it survives JSON apart from a tuple coming back as a list, so Workday's and SuccessFactors' sweeps resume.
|
||||
|
||||
**A host that cannot filter on remote is asked for the agents' world where it takes the world in one read** (ADR Fetch prep and score 1.2). Asked for "DK, SE" alone such a host never listed a remote role filed under Germany, and 18 boards fetched no new remote role outside those two countries. Phenom and the Workday tenants without a remote facet take a list of countries, so Europe is one request and the gate sorts the rest out. SmartRecruiters, SuccessFactors and Eightfold take one country a request, where Europe is the whole board (Bosch 49 pages, a SuccessFactors site 10 roles a page), so there the location read stays and the row says remote was not asked.
|
||||
|
||||
**A role whose text says remote while no field does is possibly remote, read in prep with no model** (ADR 1.1 and 1.5). A role outside the agent's locations whose remote is unstated could never "turn out to be remote": extract reads only the cut, and the cut needs the gate. 5,016 open roles were rejected that way, 805 of them saying "remote" in their text. A phrase table ("fully remote", "work from home", the Danish and Swedish words) less its denials ("no remote", "remote sensing") marks `remote_text`; the gate's remote member takes the mark as a match while `remote` is empty, and once extract has answered, prep composes `remote` from the model and the mark no longer counts. A false mark costs at most a cut slot.
|
||||
|
||||
**Switching a board or search off closes its open roles.** Only a pull that reads a target closes its roles, so a target no longer read would keep them open for good. Switched back on, the next pull reopens what it still lists. A batch in flight when the switch happens reopens them, so the settle closes every switched-off target once more.
|
||||
|
||||
**A destructive switch asks first; a reopening one queues a pull.** Switching a board or search off, replacing a board and detaching one each close roles in a tap, so the page asks first when there are roles to lose, naming the count. Switching a target on, following or setting a board, setting All locations or All roles on and saving a search each queue `pull` at once instead of waiting up to six hours for the schedule. The pull is queued in the API route, not in the page's script, so a script calling the endpoint gets what a click gets; `claim_run`'s refusal is not an error, since the run in flight or the next one reads the change.
|
||||
@@ -182,6 +186,8 @@ What was decided for roledesk and the reason for each. The target design is the
|
||||
|
||||
**`extract_batch`, `judge_batch` and `summarise_batch` run isolated, with a timeout.** `context.check()` runs only between the calls `modeltask.one` makes, not inside one, so a call that hangs was unkillable short of restarting the server; a process boundary lets a Kill, or the timeout, end it. One call is bounded at `agent.timeout`, so the deadline is a few calls' worth (30 minutes for extract, 15 for judge and summarise): a batch still running after that is stuck, not slow. The cost is that an isolated job's context has no working `stop`, `task` or `fan_out` (`context_for` in `pipeline/child.py`), so a refusal or an account-level failure inside a batch cannot spare the task's queued siblings.
|
||||
|
||||
**The profile is the CV, the languages, the prompts, the likes and the dislikes; must-haves are gone** (ADR 4.2). The must-have text with a verdict per line and a career cap at 4 was the harder form of what likes and dislikes now say softly; it left the form on 2026-10-03 and its machinery followed on 2026-10-06 (migration 34). The judge reads the languages with their levels, since a role that asks for fluent Danish against conversational Danish is a skills gap the CV text alone did not show; a change to the languages re-judges the cut like a change to the CV.
|
||||
|
||||
**Judge reads a role against a written profile, after the `/rank` of github.com/MadsLorentzen/ai-job-search.** Prompt closeness compares topics; it cannot tell a step down, years of experience or a deal-breaker, which a model reading both texts can. The profile is the CV, its languages with a level, and two soft texts, "What I like" (`like_text`) and "What I don't like" (`avoid_text`), each covering the work, the workplace and situations with no split into tasks versus environment, since the prompts already say what the owner wants. A deal-breaker is a hard rule and belongs in the fetch gate, so the form has no must-haves box; `must_text` is set only through the API. Culture is left out because it is guessed from ad text, and location because the fetch gate does it.
|
||||
|
||||
**The model reports facts and code applies the rules.** For each must-have line the model answers "met", "broken" only when the posting clearly contradicts it, or "unclear" when the text does not say, never inferred from silence; a must-have it leaves out counts as unclear. The cap is code's: a broken must-have makes career count as at most `BROKEN_CAP` (4) when a role is served (`app/models.py`), so the stored career stays the model's and the reader shows both. The CV match weights are applied when a role is served too, so changing them needs no model call. The verdicts store each line's text, so the reader still shows what a judgement was made against after the text is edited. The `input_key` carries `judge.FORMAT` (4) and the texts, so a change to the prompt's contract makes every judgement again.
|
||||
|
||||
Reference in new issue
Block a user