.gitignore's `node_modules/` rule matched directories only, so a symlink
named node_modules pointing at a contributor's absolute path was committed
(#623), broke `bun install` in CI with a dangling link and checked out as a
text file on Windows. The rule loses its slash, and security_guards gains a
check that no tracked path has a node_modules component (skipped quietly
outside a git checkout). Also qualifies the one bare `seen_jobs.json`
mention left in README.md after #617.
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
doc.get("seen", doc) raised AttributeError on a top-level array, and
entry.get("url") raised it on an entry that was not an object, so the
existing "expected an object of job entries" message was never reached.
Guard both and exit 1 with a one-line message.
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
toResult passed posted_at through verbatim, so search and detail JSON
carried "date": "2026-07-06T00:00:00Z" while every other portal CLI
emits the date part only and /scrape stores it as
posted_date: "YYYY-MM-DD". The table and plain renderers already cut the
value to ten characters, so only JSON consumers - the /scrape path - saw
the raw timestamp.
Add contractDate(): the timestamp's date part, null for an absent or
non-date value. The two tests that pinned the raw timestamp now expect
the date and fail on master, plus three cases on the helper. SKILL.md
documents the shape.
Follow-up to #608 at the maintainer's invitation. /scrape already names the full
path; the three readers still used the bare filename, which an agent can resolve
to the repo root (outside the **/job_scraper/seen_jobs.json ignore rule).
The guard test now covers all four specs; test_notion_sync_command pins the
qualified phrase. 04-job-evaluation.md is left alone on purpose: forks
personalize it, and a one-word fix there would force a framework_version bump.
* fix(jobnet-search): preserve full occupation identifiers in tables
The documented ESCO concept URI is 72 characters long, but the table renderer cut every identifier to 70, losing the last two UUID characters. Size the identifier column from its contents, retaining the existing minimum width and readable label alignment.
Exercise the actual documented occupations CLI with the README API response served over loopback. Table output must retain the same complete URI and UUID as JSON and plain output; no live portal requests.
* test(jobnet-search): cover Windows occupation fixture newlines
* docs(jobindex-search): align search examples with the actual CLI contract
The posted-today skill example omits the query that the shipped CLI requires, so copying it exits MISSING_REQUIRED. Supply a keyword and make the required flag explicit. Replace stale JSON-endpoint/card-parser search documentation with the implemented HTML Stash route and emitted field behavior.
Run the example read directly from SKILL.md through a real CLI subprocess with loopback HTTP fixtures. Keep a separate query/page routing control; no live portal requests or production-code changes.
* test(jobindex-search): cover Windows documentation newlines
* fix(portal-clis): reject missing Danish option values before dispatch
The Bunli parser discards known bare options before schema validation, silently dropping filters or applying defaults. Extend the existing pre-dispatch guards across the four Danish portals while preserving built-in switches, valued and equals-form arguments, and existing unknown-flag errors.
Actual CLI subprocess regressions deny and record every fetch to demonstrate that missing filters reach request construction on master. Valued-option and help controls keep accepted command forms covered without contacting any portal.
* docs(changelog): record fix for #573
* test(portal-clis): isolate valid flag controls from live services
The LinkedIn and Freehire positive controls spawned live search CLIs and only checked for the absence of BAD_ARG, so attempted portal requests still left a green suite. Use loopback responses and assert successful output plus the constructed freshness, pagination and result-limit contract.
LinkedIn cards are verbatim excerpts from portapulito's actual captured response in PR #153; fixture provenance and original hashes are retained. Four Danish validation suites already stop at required-argument guards and need no change. This isolates these controls rather than claiming a whole-CI egress policy.
* docs(changelog): record fix for #581
* fix(linkedin-search): preserve description paragraph and list breaks
Clean rendered description lines separately so whitespace normalization does not erase paragraph and list boundaries in JSON and plain output. Exercise the documented detail CLI against a loopback-served captured response, with field and closed-status controls.
Credits: portapulito diagnosed this behavior and supplied the captured guest-response fixture in upstream PR #153, which was closed as an accidental personalized-fork submission. This independent implementation revives only that correctness fix and its fixture evidence.
* docs(changelog): record fix for #567
* fix(jobbank-search): retain all documented repeated filter values
Declare the six array-capable search options repeatable in Bunli metadata. Without it, the CLI parser overwrites earlier occurrences before the handler receives the array, so documented OR filters only search the final value.
Exercise actual search CLI subprocesses through loopback HTTP and assert every RSS and total-count request retains repeated values. Cover all six filters, mixed equals/comma input, and unchanged single-value input; no live portal requests.
* docs(changelog): record fix for #577
"firma" joins COMPOUND_PATTERNS so the glued Danish header "Firmanavn og by"
matches again; whole-token matching since #75 skipped both sheets of the
repository's own demonstration workbook with "Could not find header row".
Every other workbook converts byte-identically. Also folds the `unreachable`
status from #564 into the seen_jobs.json schema enum in the scrape spec.
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* fix(scrape): use the full job_scraper/seen_jobs.json path in every step of the spec
Step 0 reads job_scraper/seen_jobs.json but Steps 1-4 and the rules used the bare
filename. Step 4 is where the file is written, so an agent following it literally
can create seen_jobs.json in the repo root, outside the **/job_scraper/seen_jobs.json
ignore rule, where it gets committed with the user's scrape history.
Adds a spec test that rejects bare references; relaxes the existing dedup-continuity
regex to accept the qualified path.
* docs(changelog): entry for #608
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* fix(salary): accept BOM-prefixed UTF-8 data files
Fixes#594. Thanks to @rahul05ranjan for reporting the failure and identifying the decoder change.
* docs(changelog): entry for #602
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Both specs said to match "on company + role" with "casefold + strip on
both fields", but a seen_jobs.json entry has title and no role key (the
job-scraper schema), so read literally the lookup never matched: /upskill
then weighted the same job twice, once as a tracker row and once as a
ranked entry - the double-count its dedupe step exists to prevent - and
/notion-sync split one job into two rows with different Keys.
tools/rank_state.py already does the cross-name join (tracker role
against entry title); both specs now say so.
Two derived tests read the entry schema and require the join wording to
name title for the entry and role for the tracker; they fail on master.
04-job-evaluation.md's Language Gate and job-scraper/search-queries.md's
query-language generation both read "your Languages table" from
01-candidate-profile.md, but the skeleton /reset wrote left "## Identity"
empty, so after a reset /rank and /scrape looked for a table the file no
longer had.
Carry "### Languages" and the table's header and separator rows in the
skeleton. The test derives both rows from the shipped file and pins that
the placeholder data row is not reintroduced; it fails on master.
Follow-up noted on #532.
Three date values in 05-cv-templates.md are copied straight into a CV, and
all three carried the en-dash the same file forbids:
- the in-progress-qualification snippet wrote \cventry{2025--2026}
- the \needspace snippet wrote \cventry{YEAR--YEAR}
- the in-progress section offered a date field of 2025-present with U+2013
LaTeX ligatures `--` into U+2013, so an assistant following the file produced
exactly what "Date fields must be ASCII ranges" rules out 130 lines further
down, and what /apply Step 5d then rejects. Inserting the in-progress snippet
as shipped into cv/main_example.tex and compiling with lualatex makes
tools/verify_pdf.py --ascii-dates exit 1 ("U+2013 in '... 2025-2026'"); the
unmodified template passes, and with the snippet fixed it passes again at the
same 2 pages.
these snippets predate it (#210) and were left behind. The deliberate negative
example (% en-dash, may not) and the illustrations of the forms --ascii-dates
catches are unchanged.
Found while drafting a tailored CV with an in-progress qualification, where
the snippet was followed verbatim.
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
month" and "2000-5000 requests per second" still failed /apply Step 5d:
each has a four-digit number next to the dash that happens to fall in
1900-2099, and the guide tells users to keep "--" in exactly those
prose ranges.
When both sides of the dash are bare numbers - the whole
whitespace-delimited token, outer punctuation stripped, matching
\d+(?:[.,]\d+)*[kKmM%]? with no year group among its parts - count the
match only if both are years. The salary band and the throughput range
pass; 2016-2024, 1990-2010 and "2016 - Present" still fail as before,
and a numerically formatted range (03/2016-07/2024, 01.2016 - 12.2024,
2016-03-2024-07, 2016/17-2018/19) is not a bare number on either side
and is still caught. On the stock CV with all three prose ranges on one
line, master reports three hits and this branch reports the one real
date.
Three new cases; the quantity one fails on master.
The TinyTeX snippet exports PATH for the current session only. A new terminal
window then fails with 'command not found: lualatex' although the install worked.
Add the persisted form and a one-line check.
* fix(rank): retry postings that could not be fetched instead of expiring them
A posting /rank could not fetch (403, login wall, 404, timeout, empty
page) and one that is really closed both became `expired`, which is
terminal: `candidates` only selected `new`, so a transient failure on
ranking day removed a live job from the pipeline and the report
presented it as closed.
Shape per the maintainer's decisions on #534:
- Scoring agents return a third status, `unreachable` (with a short
`fetch_error`), after exhausting the 09-web-research.md escalation
order; `expired` stays for positive evidence of closure (closed page,
410, redirect to a listing page, passed deadline). A 404 is
`unreachable` first (#538 is that case).
- `candidates` selects `unreachable` alongside `new`. `apply` increments
`fetch_attempts`, keeps `first_unreachable` (UTC timestamp) and stores
`last_fetch_error` (short reason, no page text). After 3 attempts with
at least 48 hours between the first and the last it writes `expired`
with `expired_reason: "unreachable"` and returns the job once under
`gave_up`, which Step 5 prints under "Gave up, check manually" with
its URL. A later successful fetch, an explicit `expired` or a passed
deadline clears the retry fields. `--all` still revives everything.
- rank_state.py owns the status set (`AGENT_STATUSES`); `apply` rejects
any other status instead of reporting a misleading missing score, and
test_rank_command.py asserts rank.md's JSON contract names the same
set. A new `--now` option makes the 48-hour floor testable.
- rank.md's step text (Step 2 rules and contract, rule 6's --all note,
Step 4 fields, Step 5 report, Important Rule 1) updated together.
CHANGELOG under Changed: no existing entry carries the new status, so
no migration.
Reported by @ai-tvang in #534, who also proposed the time floor and the
give-up listing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(rank): expire an unreachable posting whose deadline has passed
Review on #564:
- The unreachable branch in apply returned before the deadline check the
scored path runs, and candidates hands out `new` entries whose stored
deadline has passed. So a posting that closed on 2026-09-20 and
returned 403 on 2026-10-05 was retried, then listed under "Gave up,
check manually" as possibly live. A passed stored deadline is now
checked first and takes the expired path, dropping the retry fields,
as on master and under rule 5. New test pins it.
- 09-web-research.md step 5 said that in /rank an unretrievable posting
is marked `expired`, so an agent following it could write a 403 off
and bring #534 back. It now says `unreachable` (framework_version
1.1.2 -> 1.1.3); the CHANGELOG entry says so.
- The report shows `attempt N` instead of `N/3`, which read 4/3 while a
job waited out the 48-hour floor, and job-scraper's dedup note names
`unreachable` alongside `ranked`/`expired`.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(upstream_triage): force UTF-8 stdout and decode git output as UTF-8 (#544)
* test(tools-utf8): restore assertion in salary converter test and isolate upstream_triage test
External ads (isExternal: true) 404 on /find-job/{jobAdId} and hit the MitID login wall on /job/{jobAdId}. Route them to their employer-provided destination in jobAdUrl when an absolute http(s) URL is present.
When jobAdUrl is missing, empty, or carries an invalid/non-http scheme, fall back to https://jobnet.dk/find-job/{jobAdId} instead of emitting an empty string so downstream /scrape deduplication preserves unique URLs. Both url and jobAdUrl validate the scheme consistently.
Observation and test cases reported by NishilRathod in #557.
* fix(apply,rank): route matching portal URLs to installed CLI detail before WebFetch (#535)
When given a URL belonging to an installed portal (e.g. LinkedIn, Jobnet), WebFetch frequently encounters login walls, bot-detection blocks, or 403s. Installed portal CLIs under .agents/skills/ already provide a dedicated detail command that fetches clean posting text and structured metadata directly from board APIs.
- In .claude/commands/apply.md Step 0, invoke the matching installed portal CLI's detail command first, falling back to WebFetch on failure.
- In 09-web-research.md, place the installed portal CLI detail command as the first rung of the escalation order, bumping framework_version to 1.1.2.
- In .claude/commands/rank.md Step 2, align scoring agents to use the portal CLI's detail command before WebFetch.
- In tests/test_apply_host_check.py, add spec and resolution tests ensuring portal CLI detail precedence is strictly asserted and verified.
* fix(apply,rank): route matching portal URLs to installed CLI detail before WebFetch (#535)
When given a URL belonging to an installed portal, WebFetch frequently encounters login walls, bot-detection blocks, or 403s. Installed portal CLIs under .agents/skills/ already provide a dedicated detail command that fetches clean posting text and structured metadata directly from board APIs.
- In .claude/commands/apply.md Step 0, invoke the matching installed portal CLI's detail command first, falling back to WebFetch on failure. Derive matching portal skills from board hosts in cli/src and url-reference.md.
- In 09-web-research.md, place the installed portal CLI detail command as the first rung of the escalation order, update subsequent step references, and bump framework_version to 1.1.2.
- In .claude/commands/rank.md Step 2, align scoring agents to use the portal CLI's detail command before WebFetch.
- In CHANGELOG.md, record the framework_version bump (1.1.1 -> 1.1.2) under [Unreleased] / ### Changed.
- In tests/test_apply_host_check.py, add spec and dynamic resolution tests ensuring portal CLI detail precedence is strictly asserted and verified across all discovered installed skills.
* docs(apply): make Step 5e build artifact cleanup explicit with mechanical shell commands
* docs(apply): address review feedback on Step 5e cleanup commands and timing
* Fix fork-skip guards for local test runs
The fork skip read GITHUB_REPOSITORY with an upstream fallback, so local runs on a fork always ran the upstream-only guards. Share one helper that checks the origin remote when the variable is unset. Fixes#496.
* test: accept the ssh:// origin form in the upstream-checkout helper
An upstream clone whose origin is ssh://git@github.com/MadsLorentzen/ai-job-search(.git)
must keep running the placeholder guards; the helper only knew the https and
scp-style forms. Folded in at maintainer rebase per the #524 review.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Omarinho12345 <omarottelli720@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
A live page wrote its Jobtype item as "Fuldtid </ li >". node-html-parser
consumes well-formed markup but does not recognise a closing tag with a
space after the "<" or the slash, so the fragment became a text node and
overviewValue kept it: employmentType: ["Fuldtid </ li >"], matching none
of the documented job-type vocabulary. The same cleanText feeds every
text field on both branches.
Strip only the closing-tag shape in cleanText before collapsing
whitespace. The parser decodes entities before cleanText runs, so author
text the page encoded as <div> or <T> arrives as a literal
<div> / <T> and must stay; a probe of what the parser leaks shows only
malformed closing shapes (</ li >, </ li>, < /li>). Two fixtures: the
stray tag in both the Jobtype item and a description paragraph (fails on
master), and an entity-encoded <div> that survives.
Observed by the maintainer in the #516 merge note.
README and SETUP.md hardcoded the six shipped portals in four PowerShell/Bash
loops, so a portal added by /add-portal or borrowed from another fork was
skipped on a fresh clone. tools/install_portal_clis.py uses CI's discover-clis
glob, isolates per-CLI failures, and skips manifests with lifecycle scripts or
trustedDependencies.
The full-file skeletons for 01-candidate-profile.md and
02-behavioral-profile.md started at the "#" title, while the shipped
files open with a "---" block carrying framework_version. Applied as
written, one /reset profile left both files failing
tools/check_framework_version.py ("missing 'framework_version' in
frontmatter") and invisible to tools/check_upstream_updates.py, which
records a configuration error for a file with no local version - the
fork update path every fork is sent through.
Say to keep the frontmatter block and replace only what follows, with a
note under "Profile reset" that the marker is framework data, never
candidate data. The version is not hardcoded into the skeleton, where it
would go stale on the next bump. A derived test applies each skeleton
the way the step says and asserts the shipped file's version still
parses out unchanged; it fails on master for both files.
