c40817f932c55ff30732ded978f13631ec81b49b
35
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 kristianwindandClaude Opus 5
|
d1703dcc03 |
Check the direct-access guard by tokenising, not by grepping for it
The check asked whether "defined( 'ABSPATH' )" appeared anywhere in the file. A comment containing those words therefore passed it. Measured with a planted file whose only mention was in a comment: 15 shipped PHP files examined, every one guarded Green over a file with no guard at all — one that runs for anyone who fetches it directly, outside WordPress and outside every capability check the code assumes has already happened. This is the check with the worst consequence of being hollow, and it was hollow in the one way a grep always can be. From the cache session by way of security: a check that must RECOGNISE its own code has one blind spot per recognition method, and one that reads what the source actually says has none of that kind. PHP's tokeniser cannot be fooled by a comment, because it is the thing that decides what a comment is. ci/check-abspath.php parses each shipped file and looks for a real defined() call on ABSPATH or WP_UNINSTALL_PLUGIN. Comments and doc blocks are tokens of their own and are simply never examined. The count and the floor stay, for the reason every check here has them. Verified through the container path with php hidden from `command -v`, since static.sh runs on a Gitea runner that has no php: identical output either way. A 31st self-test assertion plants the same fixture. It is grade 2 evidence — a planted instance of exactly the failure the check describes, rather than an arbitrary trigger that only proves the check can go red at all. Two things that assertion caught about itself on its first run: The check's success line now says "parsed" where it said "examined", and the existing assertion on the count was still matching the old word. It went red rather than quietly matching nothing, which is why the wording is asserted at all. And `static.sh | grep -q` reports STATIC.SH's exit status under `set -o pipefail`, not grep's — and static.sh is expected to fail in that fixture, so the assertion read "not found" however the check behaved. The mirror image of the `go test | grep` trap already in the playbook. Output is captured to a variable first now, with the reason inline. Swept the kit for text belonging to other plugins while here, after cache found a comment in its copy describing security's tree: no NLSEC_/NLCAC_ references, and every path named in ci/ and tests/ either exists here or is WordPress core. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
bf4b429014 |
Put a Discounts card on the shared Nolimit dashboard
The dashboard showed Cache, Security and Assistant and not this plugin. Being
absent from the dashboard is a different failure from being absent from the
menu, and Kristian hit them in that order — so each now has its own assertion
rather than one standing in for the other.
The card registers on wpmgr_dashboard_cards with the counts this plugin exists
to report: groups, and addresses currently receiving a discount.
Cached for five minutes. The contract says implementations must not measure
anything in that filter, because it runs on an admin page load and a slow card
makes somebody else's dashboard slow in a way they cannot attribute to us. Two
COUNT(*) on small indexed tables is the most this may cost, and the dashboard
is a page people leave open.
Status is warn rather than fail when nothing is configured: a shop that has
installed this and not set it up yet is unfinished, not broken. Reserving red
for actual breakage is what keeps red worth reading.
Two assertions, proven red by removing the add_filter:
FAIL this plugin puts a card on the shared dashboard — 0 card(s) registered
FAIL and it carries this plugin colour, not WooCommerce purple
— expected '#1a7a52', got NULL
The colour is matched against the literal, not against a constant. The shared
file renders whatever colour it is handed, so a card asserting its own constant
would agree with itself after somebody put WooCommerce purple back — the same
self-agreeing shape as the REST namespace assertion.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
4c7731ae01 |
Assert the page really lands under the Nolimit menu, and bump to 1.5.0
Kristian's menu screenshot showed four plugins under Nolimit and not this one, after a build that moved the page there had already merged. Two separate problems behind that. The version never moved. The rename and the menu change went out still calling themselves 1.4.6 — the same number as the copy already installed. So two different builds carried one version, which is the one thing a version number exists to prevent, and nothing offered the new one as an update. Now 1.5.0. And the tests could not have caught it if the code HAD been wrong. The only menu assertion was that this plugin claims the label through wpmgr_menu_title — which passes while the plugin is absent from the menu entirely. The label and the membership are different facts, and the screenshot showed exactly that pair: the menu said Nolimit, this plugin was not in it. Three assertions now. The parent exists after wpmgr_ensure_menu(), this plugin's page is among the children of WPMGR_MENU_SLUG, and — separately — the main file lists includes/shared-menu.php in its is_admin() branch. That third one is there because the first two are a reduced repro and say so: the admin menu is only built in an admin request, and these run under WP-CLI where is_admin() is false and class-admin.php is never included, so the test has to require the files by hand. A by-hand require would pass even if the plugin never loaded them in a real request. That is the half a reduced repro always omits, so it is asserted on its own rather than assumed. Checked while here, from the security session's report: no human_time_diff anywhere in this plugin, so the half-translated "4 timer ago" seam does not exist here. Nothing to fix. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
ae4112c773 |
Publish releases to kw/nolimit-discounts-dist and point the header there
The family shape is source private, releases in a separate public repo so a shop can fetch an update without credentials and without the source being readable. This plugin was the only one still serving its own update feed out of the repository that holds ci/, docs/ and tests/. kw/nolimit-discounts-dist created (public, zips only). RELEASE_REPO in ci/plugin.conf now names it, and ci/publish-release.sh honours it over GITHUB_REPOSITORY — falling back to the running repo, which is what a plugin without a split still wants. 🔴 The "Update URI:" header moves in the SAME commit as the publishing target, and ci/static.sh now fails when the two disagree. The header is what every installed copy polls; if it names a repository nothing is published to any more, the shop stops being offered updates and nothing announces it, because latest_release() simply returns false. That is the same failure as a privacy page standing still while the code moves, and the check is what makes it impossible to forget. Proven red before being believed: pointing RELEASE_REPO at another repository fails with both sides named. RELEASE_REPO is required by ci_load_conf, because an unset value would turn the comparison into a no-op and restore exactly the bug it prevents. Not done here, and it is the blocker for actually cutting a release: publishing to another repository needs a token with write access to it. The job token only covers the repo it runs in, so this needs a cross-repo PAT in the repository secrets, and that is Kristian's to add. Also not done, deliberately: the source repo stays public for now. Making it private before the dist repo has releases would break the feed for the copy installed on the live shop, whose header still points at the old address. 1.4.6 and earlier keep working through Gitea's rename redirect - measured, the old name still answers 200 - and that redirect is the only thing holding them up, so it must not be removed until a build carrying the new header has propagated. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
9f19688900 |
Rename to Nolimit Discounts and move the page under the shared menu
Kristian could not find this plugin in the Nolimit menu, and it still called
itself WooCommerce Email Discount Manager. Both are the display side of the
family rename; neither touches the installed folder.
Plugin Name is now "Nolimit Discounts". The folder, the text domain, the option
prefix and the three tables are deliberately unchanged: WordPress identifies a
plugin as <folder>/<file>, so renaming the folder would not move the
installation on the live shop — it would put a second copy beside it and leave
the old one active. That is a migration with a shim, and it is Kristian's call
rather than a side effect of a label change.
includes/shared-menu.php added, byte-identical to the family copy
(f4862d5c…c63185), and the page moved from the WooCommerce submenu to the
shared parent. The page slug is unchanged, so admin.php?page=… still resolves
and an existing bookmark keeps working — moving a page between parents does not
move its URL.
The label is claimed through the wpmgr_menu_title filter from this plugin's own
bootstrap, NOT by editing the shared file. Which copy of that file a site loads
is decided by activation order, and PHP cannot un-declare a function, so the
first copy wins for the whole request: editing it would make a site with three
of five plugins updated show "Manager" or "Nolimit" depending on who booted
first, and change its mind when a plugin is deactivated. The filter is
idempotent and a plugin still on an older build changes nothing.
The filter is registered before the WooCommerce gate, for the same reason the
updater is: the shared menu's label must not depend on whether this particular
plugin got past a check.
Two assertions, both proven red first. The label is asserted through the filter
rather than by reading the menu, because the menu is only built in an admin
request and the smoke tests run under WP-CLI. And the shared file's sha256 is
asserted, so editing it goes red here rather than going strange on a shop —
appending one comment line produced:
FAIL and the shared menu file is the family copy, unedited
— expected 'f4862d5c…', got '45df6b55…'
Also caught in passing by the kit, working exactly as intended: the new
shared-menu.php was untracked, and "every file the plugin loads is a file the
release contains" failed rather than shipping a zip without it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
dd0afb8a3c |
Answer the update filter even when the release feed cannot be reached
offer_update() returned $update untouched when latest_release() failed. A
plugin that answers neither way is in NEITHER the response nor the no_update
list, and WP_Plugins_List_Table builds the per-plugin "Enable auto-updates"
link from that transient — so the row reads "Auto-updates are not available for
this plugin". That reads as a setting rather than as a failed HTTP request, and
the shop quietly stops being offered fixes with nothing saying so.
Found by the woo-ai-manager session, which installed all five plugins in one
WordPress and dumped the update_plugins transient: this plugin appeared in
neither list.
Measured here before fixing, rather than taken on report. The existing tests
covered the feed answering with a newer version and the feed answering with the
same version — nothing covered the feed not answering at all. Writing that case
first produced:
FAIL an unreachable feed still answers with the installed version
— expected '1.4.6', got NULL
So the bug is real in this tree, and the test is sensitive to it.
The no-release branch now answers with the installed version, which is true and
comparable, so WordPress files it under no_update and the row behaves normally
until the feed answers again.
The icons array is now built once and shared by both branches. It was two
separate literals, and the failure mode of that is precisely the one being
fixed: the branch added later is missing them, and Dashboard -> Updates shows
the grey default plug for as long as the feed stays down. A second assertion
covers it.
Note on the diagnosis offered with the report: the guess was that
latest_release() fails here because Update URI points at the source repo rather
than a dist repo. That does not hold up — the feed resolves and the repo is
anonymously readable, and the update assertions pass against a real response.
The observation is still consistent with this bug, though, because ANY feed
failure produced it. The fix is robust either way, which is why it does not
wait on the dist-repo question.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
9901efd8b2 |
Assert the REST namespace by name, not against its own constant
tests/smoke.php filtered the registered routes by WC_EDM_REST_API::REST_NAMESPACE and then asserted that the filtered list was non-empty. That agrees with itself whatever the constant says: rename it and the routes are still "registered", while every caller already integrated against wc-edm/v1 gets a 404 and nothing goes red. Pointed out by the woo-security-manager session, which had the same shape in its own tree — an assertion that derives its expected value from the thing it tests is agreeing with itself, and would pass somewhere no plugin had ever been installed. wc-edm/v1 is the one string in this plugin that somebody else's code depends on by name, and it is exactly the kind of thing a rename quietly takes with it. The namespace is now spelled out in the test. Proven red before being believed: changing the constant to 'nolimit-discounts/v1' fails the new assertion and names both sides — "expected 'wc-edm/v1', got 'nolimit-discounts/v1'". Green on unchanged code. Two nearby assertions checked and deliberately left alone. The DB-version one compares WC_EDM_VERSION against the option the activation routine wrote, which is two independent sources rather than one. The update-URI one asserts a property (non-empty, https) and says so. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
8528b94c2d |
Drop WooCommerce's brand purple from the plugin icon
assets/icon.svg filled the badge, the envelope fold and the percent sign with #7f54b3 — WooCommerce's own brand colour. Caught by the odin session during the trademark review. The point of taking "Woo" out of the plugin names was to stop implying an official tie to Automattic. A mark that keeps their purple says visually exactly what the rename stops saying, and a colour is harder to defend as coincidence than a name. It is wrong independently of what the family palette ends up being, so it does not wait for that decision. #1a7a52 chosen to match the old colour's WEIGHT rather than merely to differ from it: 5.32:1 on white against the purple's 5.50:1, so the white envelope and badge keep the contrast the proportions were tuned for at 40px — the size WordPress renders this at on Dashboard → Updates. Green also reads as savings. The hex of the colour being avoided is written broken up in the comment (7f-54-b3). A palette check across the five plugins would otherwise match this explanation and report the icon as still carrying it — the same self-matching trap the credential scan hit earlier today, when the rule flagged its own documentation. Not included, because it belongs to the rename and that is still Kristian's decision: the aria-label still reads "WooCommerce Email Discount Manager", which is the plugin's actual name today. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
ad9e55d83e |
Make the site test's resource names unique per run, not per PID
The Gitea site test has been red since
|
||
|
kristianwindandClaude Opus 5
|
d64d0fd1a8 |
Stop ci/site-test.sh leaking a MariaDB volume on every run
`mariadb:lts` declares VOLUME /var/lib/mysql, so every run creates an anonymous volume — and `docker rm -f` does not remove anonymous volumes. Only `docker rm -f -v` does. What hid it: cleanup() removed the containers, the network and the NAMED $id-wp volume correctly. Three of the four things the run creates. Removing three of four is indistinguishable from removing all four unless you count, which is the same shape as every other bug found in this kit today. Found by the subscriptions session, which traced the Gitea runner's disk being 100% full — 26 GB in 95 volumes with 1 in use — and by woo-cache-manager from the other end, whose push failed with `unable to create temporary object directory`, three layers away from the cause. Measured here rather than taken on report: a mariadb:lts container creates exactly one anonymous volume, it survives `docker rm -f`, and it is removed by `docker rm -f -v`. This machine was holding 133 volumes, 127 dangling, 15.2 GB reclaimable. The fix is the -v. The rest is so it cannot come back silently: cleanup() now asks the containers which volumes they own, via docker inspect, BEFORE removing them, and checks afterwards that none survive. Attribution rather than a global before/after count on purpose — several sessions share this box and run these container pairs concurrently, so a neighbour's volume would read as this run's leak. The check is advisory on a run that already failed, and fatal on one that otherwise passed: site_test_ok is set at the single point the run is known to have succeeded. And it calls exit rather than return, because `return` from an EXIT trap does not change the script's exit status — the warning would have printed while the build went green, which is the failure mode this whole day has been about. Verified: the real site test now runs green with a volume delta of zero. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
8121ca18dd |
Make the self-test run on Gitea, where it has been failing since it landed
ci/selftest.sh called `php` directly, four times. The Gitea runner image has no php — which is exactly why ci_php exists and says so in its own comment — so Static checks has been RED on Gitea since the self-test merged, while GitHub stayed green throughout. Found only by going to look at the other forge. Two of the four assertions failed there. The other two passed FOR THE WRONG REASON, and that is the worse half: they expect a non-zero exit, and `php: command not found` is a non-zero exit. A green tick for a check that never ran is the precise thing this script exists to prevent, reproduced inside it. Fixed by routing every call through ci_php, and by moving the fixtures inside the repo copy and staging them: ci_php's container gets its filesystem from `git ls-files`, so a fixture outside the repo or left unstaged is simply not there. selftest-empty/ carries a .keep file because git cannot track an empty directory, and an absent directory would make the check fail for a different reason than the one being asserted. Verified through the container path with php hidden from `command -v`, not just locally where php exists: all four verdicts identical either way, and the annotated path still resolves to includes/class-db.php. New 30th assertion: no ci/ script may call an interpreter directly. Its first version flagged five lines, all false: string literals mentioning php, and the calls inside the docker scripts in static.sh and site-test.sh, where php is correct because the container is a php image. Its second still conflated python3 with PyYAML. The runner HAS python3 and has NO php, and PyYAML is the only missing module — so bare python3 over the stdlib (build-zip.sh's zipfile, publish-release.sh's JSON readers) is correct and is not flagged. Measured, so the rule is not uniform. Controlled both ways: zero hits on this tree, and all four bare-php lines caught in the version that broke Gitea. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
bd058566f5 |
Parse the workflows on Gitea too, and keep the compat matrix off its runner
Both found by the subscriptions session in its copy of this kit, and both reproduce here. They share the shape everything else in ci/ has had: the failure is invisible on GitHub, which is where anyone would be looking. 1. ci/workflows-in-sync.sh never parsed the workflow files on Gitea, and printed "Workflows: in sync." anyway. It skipped with a note when PyYAML was missing — and PyYAML is missing in exactly one place. Measured here rather than taken on report: `import yaml` on gitea/runner-images:ubuntu-latest raises ModuleNotFoundError. So the check was switched off on the single forge where an unparseable workflow produces no run at all, no failed run and no error to click on, which looks exactly like a runner that has not picked the job up. ci_python_yaml in ci/lib.sh now falls back to a container the way ci_php already did — alpine + py3-yaml, no network install, one apk call. There is no skip path left: workflows that cannot be parsed are a failure, not a note. Both routes verified to give byte-identical output. 2. compat.yml ran its five-cell matrix on Gitea for every PR touching ci/ or tests/. The `schedule` was gated to GitHub for exactly this reason and `pull_request` was forgotten. The subscriptions repo measured six jobs dying together with exit code 137 — SIGKILL, runner out of memory, two seconds in, without one error message in the log. Latent here only because this repo merges through GitHub and never opens a Gitea PR; one Gitea PR touching ci/ would have found it. New ci/check-workflows.py enforces both, called through ci_python_yaml. It parses every workflow and fails when a Gitea job with more than one matrix cell is not gated, and it is fatal when it parsed no file at all. 🔴 Its first version asked whether the `if:` CONTAINED the server_url test, and passed the very condition it exists to catch: `!= 'schedule' || server_url == ...` contains the gate while letting pull_request through. Substring matching is adjacent to the signal rather than the signal. It now compares the whole normalised condition against an allowlist, and was checked both ways in one run — red against the unfixed compat.yml naming the job and the cell count, green after. Three self-test assertions added, 29 total: an unparseable workflow fails, an ungated multi-cell matrix fails, and parsing zero files fails. Two notes from building it, both the same trap this kit keeps setting. The container path could not find check-workflows.py because ci_in_container tars `git ls-files` and the file was untracked. And the ungated-matrix fixture used | as a sed delimiter while the gate itself contains ||, so sed silently changed nothing; the assertion reported "could not stage the fixture" instead of passing, which is the only reason it was noticed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
d0dcbd2c55 |
Assemble the self-test's fixture values instead of writing them literally
CI caught this on the previous commit's first push: the credential scan flagged
ci/selftest.sh itself, twice. The file is tracked, the scan reads every tracked
file, and the fixtures were credential-shaped literals sitting in it.
It passed locally because I ran ci/static.sh before `git add`, so selftest.sh
was still UNTRACKED and therefore invisible to a scan reading git ls-files.
That trap is documented four lines into the same file, about the fixtures it
plants. Knowing it and applying it to your own validation are two different
things, and the second is the one that counts.
Fixed by assembling every fixture value from pieces, which is stronger than any
exemption:
- A filename exemption would switch the scan off in ci/ and tests/, which is
exactly where a key gets pasted to test it. A sibling plugin reached the
same conclusion from the other side when its redactor fixture went red.
- A placeholder marker in the value would stop the fixture triggering the
check it exists to trigger.
- Split literals leave the WRITTEN file fully credential-shaped while the
SOURCE contains no matching string at all, so nothing needs excusing.
Verified both directions: the source no longer matches any pattern in the scan,
and each assembled value still does. static.sh green on the real tree with
selftest.sh tracked (45 files read, up from 44), self-test 26/26.
The pipeline worked as designed — static.sh runs before selftest.sh in the
static job, so the real tree was checked first and the failure named the file
and both rules. Nothing about this needed a human to notice.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
0a58661864 |
Add ci/selftest.sh: prove the checks can still fail
Three rounds of fixes to this kit, and each round found the previous round's blind spot: a check that examined nothing, then a check that examined everything with a pattern that could not match, then a flag that made one rule skip binary files without a word. None of them were visible from a green run, and each was found by a sibling plugin rather than by anything here. So the battery stops being a shell loop somebody retypes and becomes a script CI runs. 26 assertions: 13 credential shapes that must be flagged, 6 lookalikes that must stay quiet, the direct-access count, the four text-domain verdicts, the annotated path being a real file, and a plugin.conf with its floors stripped failing to load. 🔴 It asserts on the thing that has CONSEQUENCES — the exit status of the script CI runs, and the specific failure message. Never a filename, a count, or a log line that merely sits near the signal. The previous ad-hoc battery asserted "the fixture's filename appears in the output", which passes on grep's own `binary file matches` diagnostic, because that diagnostic prints the filename in exactly the place a real failure would. A sibling plugin recorded two binary cases as PASS on that basis. The probe had the same defect as the check it was testing. The self-test was then checked to go red: making the AKIA pattern inert fails exactly one assertion, naming the shape. Its first run failed an assertion, and the fixture was at fault rather than the product. This script sources ci/lib.sh, so the floors are in the environment and a plain subshell inherits them — ci_load_conf then passed over a plugin.conf that does not define them. Fixed with an explicit unset, and the reason is inline so nobody weakens the assertion instead. A failing probe is evidence about the probe until you have looked at it. Wired into the static job in BOTH workflow roots, byte-identical: .gitea hides .github completely rather than merging it, so a step added to one root only would not run on Gitea and would look exactly like a runner that had not picked the job up. ci/workflows-in-sync.sh passes. Excluded from the release zip, and it plants nothing in the real tree — the fixtures go into a throwaway copy under mktemp, several being credential-shaped by definition. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
f3126b57e6 |
Stop the credential scan silently skipping binary files
Adding the name-anchored rule in the previous commit also put `-I` on the
value-pattern grep, which it did not have before. grep -I SILENTLY SKIPS a file
it decides is binary, so a PEM header inside one is waved through without a
word. Without -I the same file reports "binary file matches" and fails, which
is the right direction to be wrong in for a check whose whole subject cannot be
unpushed.
Nothing went red to announce this. The tree has no binary tracked files today,
so the narrowing was invisible from both sides — the clean run stayed green and
no probe covered it, because every probe so far planted a text file at the repo
root. It is the same class as the hole this scan already had: a check that
cannot match anything and a check that matches nothing print the same line.
The two rules now differ on -I deliberately, each with the reason inline. The
name rule keeps it: that one is heuristic, so a chance match inside a compiled
asset is noise rather than a finding.
Also proven, rather than asserted, after a sibling plugin found its own scan was
reading only the SHIPPED file list and therefore missing 36 of 73 tracked files
— every CI script, workflow and test fixture, which is exactly where a key gets
pasted to test it. This scan reads `git ls-files` and always has, but the claim
had never been measured: probes in ci/, tests/ and .github/workflows/ are all
caught while `dist-files.sh` lists none of them.
Battery now 19, both directions, through ci/static.sh:
13 fire — AKIA, PEM, sk-ant-, sk-, ghp_, gho_, github_pat_, array form,
define() form, the same key in ci/ and tests/ and .github/, and a
PEM header inside a binary file
6 quiet — a bare hash, an unfilled placeholder, a masked value, an empty or
short value, a comma after 'token' in ordinary code, and a define
whose value is still TODO
The comma control comes from the sibling plugin: it put `,` into the shared
alternation and had to prove `wp_die( 'token', 'a long sentence' )` stays
quiet. This tree anchors the comma case on `define(` instead, so the same
string was never at risk — but it is worth a control either way.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
82d6cc7d7d |
Close the inert-pattern hole in the credential scan
A count proves the scan READ a file. It says nothing about whether the pattern can match anything — and "now it reports a number" and "now it only reports a number" print the identical line. The woo-ai-manager session proved this the hard way: it planted an AWS key, watched its file count rise from 37 to 38, and the scan passed green. Its prefix list had no AKIA entry at all. This tree's list did have AKIA, but the proof behind that claim was a grep of the regex in isolation, not a run of ci/static.sh — a stub harness that proves the pattern compiles, not that the check fires. Re-done properly: every shape the pattern claims to catch is now planted in a tracked file and run through the whole script. That exercise found a real hole. A prefix list matches the shape of a VALUE, so it is blind to any credential with no vendor marker: an api_key assigned twenty opaque characters walked straight past it. Added a second, name-anchored rule that fires only where the code itself calls the value a secret, covering both the array/assignment form and define(). It is not an entropy heuristic — the file's existing refusal of those still stands, because they fire on minified assets and hashes and a check that cries wolf gets commented out. Placeholders are excluded, or the rule would go red on the one thing a settings screen is guaranteed to contain. Proven from both sides, through ci/static.sh rather than in isolation: 9 shapes planted and all 9 flagged (AKIA, PEM, sk-ant-, sk-, ghp_, gho_, github_pat_, array form, define form), and 4 lookalikes correctly ignored (a bare hash, an unfilled placeholder, a masked value, an empty/short value). 13/13. The one false positive measured was this change's own explanation: the first version of the comment spelled the example out in full and the rule flagged it. Fixed by writing it in prose. Deliberately no bypass marker — an unexercised escape hatch is its own hollow check; add one when a real documentation case needs it. Note for the sibling plugins: an untracked fixture is invisible here, since the scan reads git ls-files. A probe planted without `git add -N` passes clean and looks like the scan working. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
9b0b0ab475 |
Make the CI checks say how many files they actually read
Four checks in ci/ printed a reassuring line having examined nothing. Found independently by the woo-ai-manager and woo-cache-manager sessions in their own copies of this kit; all four reproduce here. A check that examined nothing prints the same sentence as one that examined everything, and only the passing side can tell them apart. That is why these survived being verified: a pattern that is too broad fails loudly the first time it meets real code, while one that finds nothing passes forever. So every success line now carries a count — the old text domain line could not tell 142 from 0. - static.sh, direct-access guard: counts what the loop examined and fails below MIN_SHIPPED_PHP_FILES. shipped_files() swallows a dist-files.sh failure with `|| true`, so an empty list is one broken .distignore away, and this is the check standing between a PHP file and being requested straight from a browser outside every capability check the code assumes has happened. The floor is above 1 because a pattern that wrongly excludes includes/ collapses the list without emptying it. - static.sh, credential scan: counts what it read, fatal on zero. A pushed key is compromised even after the commit is deleted, so a silent no-op here is not a weak check but the absence of one wearing a green tick. The floor is 1 and is not configurable: this list has no filter that could go partially wrong, so the only way it misreports is by coming out empty. - check-textdomain.php: three zeros, three verdicts. No PHP files at all is always fatal and deliberately not caller-configurable — it says the scan root is wrong, not that the plugin is small. Below --min is fatal. Zero calls with no --min is a warning, since a small plugin may legitimately have no translatable strings, but it is never silent. - check-textdomain.php: fix the annotated path. str_replace( $root, '', $path ) with the default root of "." removed every dot anywhere in the path, so a real error in includes/class-db.php was reported on "includes/class-dbphp" — not a file, not clickable, and not greppable. Every error this script printed with the default root was mangled that way. The floors live in ci/plugin.conf, the only file under ci/ that knows anything about this plugin, rather than hardcoded in static.sh: static.sh is copied verbatim between plugins too, so a number in it would make this plugin's shape everybody's constraint. ci_load_conf now requires them — an unset floor turns its comparison into a no-op and silently restores the bug. Each floor was broken once and watched to fail before being believed: empty shipped list, wrong scan root, --min above the real count, zero calls without --min, empty credential list, and a plugin.conf missing both floors. Static checks green, and now report 13 shipped PHP files, 142 translation calls across 17 files, 44 tracked files read. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
f14c51dcf2 |
Rename the repository to woo-discount-manager, keep the installed slug
Kristian named the five plugins as a family, and three repos disagreed with what
he calls them. His decision: rename the repo, never the installed slug.
MEASURED BEFORE DOING IT, because four published releases carry the old URL in
their Update URI header. A throwaway repo was created, renamed and deleted:
old API path 301 -> new
old web path 301 -> new
old /releases/download/... path 301 -> new
and WordPress follows up to 5 redirects by default (class-wp-http.php:191), on
GET. Confirmed afterwards against the real thing: the old feed URL resolves to
v1.4.5 and the old download path still serves 48185 bytes.
So a shop on 1.4.2 keeps updating through the redirect, and 1.4.6 moves it onto
the new address directly.
PLUGIN_SLUG and PLUGIN_MAIN are deliberately untouched and now disagree with the
repository name. That is permanent: the installed directory has been
woocommerce-email-discount-manager since the first release and is on a live
shop, and changing it would not move that installation — it would put a SECOND
copy beside it and leave the old one active. ci/plugin.conf says so in the file,
because otherwise somebody will helpfully align them.
Also in, both for the family rather than for this plugin alone:
- docs/REUSE.md gains the hostname-keyed hook as a first-class section. It is
the only bug we have found that is CAUSED by there being more than one plugin,
so it is invisible to anyone reading a single repo — along with the same shape
in a shared-*.php file copied into five plugins, which fatals with "Cannot
redeclare" on the second activation without function_exists() guards.
- ci/static.sh fails on anything shaped like a credential in a tracked file.
Suggested by the AI-manager port: a pushed key cannot be unpushed, only
rotated. Deliberately narrow — sk-ant-, sk-, ghp_, gho_, github_pat_, AKIA,
PRIVATE KEY blocks — because a broad entropy heuristic fires on minified
assets and a check that cries wolf gets commented out.
Verified failing before being believed: a file containing sk-ant-api03-... makes
the step report the filename and the suite exit 1.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
cbad402656 |
1.4.5
Gets the cross-plugin fix onto a shop. Until this is installed, a plugin updating from the same host can be offered this one's release as its own, and the direction that breaks in is decided by load order. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
b5b4bc2e03 |
Answer only for our own plugin, not every plugin on the host
🔴 Live-shop bug, found by the subscriptions session with a screenshot. `update_plugins_{$hostname}` is keyed on the HOSTNAME, not the repository. Every plugin updating from gitea.nolimit.dk shares the single hook `update_plugins_gitea.nolimit.dk`, and WordPress runs every callback on it for every one of those plugins: $update = apply_filters( "update_plugins_{$hostname}", false, $plugin_data, $plugin_file, $locales ); This updater registered with `10, 2` — so it never received $plugin_file — and returned its own release unconditionally. Result on a live shop: a subscriptions plugin was shown this plugin's 1.4.4 and told it was an update for itself. Load order decides which callback wins, so the direction it breaks in is arbitrary: a rename, a different folder name, a plugins_loaded priority change, and it flips. If it flips this way round, a plugin with auto-updates enabled installs somebody else's zip over itself, unattended, on a shop taking money. Both halves are the fix. `10, 3` so the argument arrives, and a check that the file WordPress is asking about is ours. With the count left at 2 the guard would compare against an empty string and silently do nothing — the same shape of bug it exists to fix. tests/smoke.php now calls offer_update() with a foreign plugin file and requires false back. The site test installs exactly one plugin from this host, so the collision cannot arise there on its own: that assertion is the defence. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
416c74ac5b |
Answer the details modal, and make two dead checks check
wp-admin builds "View version details" as
plugin-install.php?tab=plugin-information&plugin=<slug>, which calls
plugins_api() — which asks wordpress.org. This plugin is not there, so the link
opened a modal reading "Plugin not found." on the same screen that was telling
the shop owner an update was ready. Seen on the live shop, not inferred.
The filter is answered here now: name, version from the feed, author, links,
compatibility, and the release notes as the changelog — escaped rather than
rendered, because a release body is not a template language. Another plugin's
slug falls through untouched, with an assertion on that: answering for somebody
else would replace their modal with ours.
Two checks in ci/update-smoke.sh could not fail, both found by the subscriptions
port, both sitting under a comment explaining exactly what they were for:
- the plugin directories were counted into a variable that was never read. The
comment above it describes a zip installing a SECOND copy beside the first;
nothing tested it. Now: directories starting with the slug, exactly one.
- the last step ran `wp eval 'echo WC_EDM_VERSION;'`, hard-coding this plugin's
constant into a script that is copied between plugins. Elsewhere it printed
an empty value and carried on. The name is read out of the plugin header now
and the value is compared against the version that was installed, because
files can be replaced while the running code still reports the old version.
Both verified failing before being believed: copies=2 and copies=0 fail,
running != expected fails, and a plugin with no *_VERSION constant takes the
branch that says so instead of comparing against an empty string.
CORRECTION to the note added with the release-id fix. It said those four
releases published correctly "because this instance's author id is -1". That is
wrong in a way that invites relaxing: gitea.nolimit.dk is one instance and both
plugins publish to it. The difference is WHO publishes. A release created by the
Actions job token has the ghost user as its author ("id":-1) and the minus sign
hides it from [0-9]+; a release created by a real user — a cross-repo PAT, or
one published by hand — has "id":1 and the greedy match lands on it. Verified:
this repo's latest release reports {'id': -1, 'login': 'Ghost'}. Corrected in
CLAUDE.md and docs/REUSE.md.
docs/REUSE.md gains "Make a check fail once before you believe it", listing all
three dead checks found today. A green build is exactly what a broken check
looks like.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
db3658c422 |
1.4.4
The fifteen-minute cache is the only change here a shop can feel, and it is the one Kristian hit: a release published and nothing shown. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
43816fdecc |
Read the release id out of JSON, not out of a greedy regex
ci/publish-release.sh found the release id with
sed -n -E 's/.*"id":[[:space:]]*([0-9]+).*/\1/p' | head -1
`.*` is greedy, the response is one line, and a Gitea release payload carries
an embedded "author" object and — once anything is attached — an "assets"
array, each with an id of its own. So it matches the LAST id, not the release's.
Measured against the four published releases here: their real ids are
416/417/419/421, and that pattern returns 1/2/3/4, which are the asset ids.
All four were nonetheless published correctly, and only by luck. The author id
on this instance is -1, the minus sign stops `[0-9]+` matching, and a create
response has no assets yet — so the last numeric id happened to be the
release's. A real author id, a Gitea that orders its fields differently, or a
re-run against a release that already has its zip, and it picks a number that
belongs to something else. Release 4 does not exist in this repository, so a
re-run of v1.4.3 today would 404 loudly rather than attach the zip to a
stranger's release, but that is the blast radius by accident, not by design.
Found by the session porting this into subscriptions, where the same line
picked the author id and the upload 404'd on its first real release.
json_field() reads one top-level field with python3, which release.yml already
requires. Verified against the live responses: 416 and 421 where the sed gives
1 and 4, and empty rather than a traceback on empty input, on "Not found." and
on an error object.
Two guards added with it, both verified against the live v1.4.3 release:
- the id's tag_name must equal the tag before anything is uploaded to it. The
failure worth guarding is not a 404 — that is loud — but an id that exists
and belongs to something else, which would attach this plugin's zip to an
unrelated release with every check still green.
- a re-run skips the upload when the zip is already attached, instead of
failing on the half that previously succeeded.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
a1f6e54f9d |
The smoke test could not fail, and other people's eyes
Four fixes, two of them serious, three of them found by the session porting
this into subscriptions.
1. THE SMOKE TEST COULD NOT FAIL. `wp eval-file` runs the file through eval()
INSIDE A METHOD, so the top level is function scope. `$wc_edm_failures = 0`
at the top and `global $wc_edm_failures` in the helper were two different
variables: the helpers incremented the real global, the verdict read the
local, and the local was always zero.
Measured rather than reasoned. A deliberately false assertion added to the
unmodified file:
FAIL DELIBERATE FAILURE — this run must go red
All assertions passed on WordPress 7.1 with WooCommerce 11.1.0.
EXIT=0
and with the fix, the same forced failure:
FAIL DELIBERATE FAILURE — this run must go red
1 assertion(s) failed on WordPress 7.1.
EXIT=1
The FAIL lines always printed, so failures found by reading the output were
real finds. What was broken is the CI gate: a regression on either forge
would have gone green. Four lines at the top now prove the counter reaches
the verdict before anything relies on it — this is the one file whose whole
job is to be able to go red, so it checks that it can.
2. `git ls-files` QUOTES NON-ASCII PATHS. "TESTMILJØ.md" comes back as the
literal string "TESTMILJ\303\230.md", which matches no pattern in
.distignore, so the file is kept — an internal document walking into the
release zip with nothing said. Fixed in ci/dist-files.sh and in
ci/static.sh's trailing-?> check, which had the same bug and would have
silently skipped the file it exists to check. Verified by adding such a
filename and watching it be excluded. `done < <(...)` rather than a pipe, or
the loop runs in a subshell and the failure counter stops incrementing.
3. THE FEED CACHE WAS SIX HOURS, and Kristian hit it: a release published and
his shop shown nothing. The reasoning ("WordPress checks twice a day") was
wrong. WordPress gates its own check by screen in wp_update_plugins() — one
minute on Dashboard → Updates, one hour on Plugins, 2–12 hours in the
background — so WordPress is already the rate limiter and a longer cache
only hides releases underneath it. Fifteen minutes now, pinned by an
assertion.
4. The wp_update_plugins() assertion made a real HTTP request, because the
force-check tests had just deleted the transient. It passed only because
this feed repo is public, which made it measure the environment rather than
the code. Re-primed first.
ci_in_container() replaces the inline docker plumbing in ci_php(), taken from
the subscriptions port: the script goes in as a file rather than interpolated
into `sh -c`, and --entrypoint sh matters for images whose entrypoint swallows
its arguments.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
056be0e917 |
Credit the plugin to its actual author, and 1.4.3
The header went out as "Author: WEDSMP" with a Plugin URI of example.com. That is what wp-admin shows to whoever installs it, which is why it is worth a release of its own rather than waiting for the next change. Author is now Kristian Wind, with an Author URI pointing at where the source lives, and the readme credits kristianwind rather than wedsmp. ci/static.sh now fails on a placeholder in the header. It catches the generic markers — example.com, TODO, yourname, an unfilled <...> — and it would have caught the Plugin URI. It would NOT have caught "WEDSMP": a made-up vendor name is indistinguishable from a real one to any check, so an empty field is warned about and a wrong-but-plausible one cannot be. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
15f88db2c4 |
1.4.2
Puts the icon and the working Check again link in front of a shop. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
200f791f40 |
An icon, a Check again that checks, and the auto-update rule written down
Three gaps found by being asked plain questions about it.
**The auto-update toggle was a promise nobody had checked.** offer_update()
answers even when the installed version is current, on the reasoning that the
answer has to land in WordPress's no_update list for the "Enable auto-updates"
link to exist at all. That was a comment and an intention; it is now an
assertion against the real WP_Plugins_List_Table, which is where the flag is
actually read:
$plugin_data = array_merge( (array) $plugin_info->no_update[ $plugin_file ],
array( 'update-supported' => true ), $plugin_data );
A plugin in neither response nor no_update gets "Auto-updates are not available
for this plugin" while looking entirely healthy.
**An icon.** Without one, Dashboard → Updates shows a generic grey plug.
assets/icon.svg, handed over in the offer's icons key, served from the shop's
own copy rather than the release host — one fewer thing that must be reachable
for wp-admin to render, and it cannot go mixed content on an HTTPS shop. Drawn
as paths rather than <text>: an SVG that leans on a font renders differently on
every machine, and this one is shown at about 40px, which is the size where
that is the difference between a mark and a smudge.
**"Check again" now checks again.** The six-hour cache is right for the check
WordPress runs twice a day and wrong for a link whose whole promise is that it
looks now. Publishing a release and then clicking it showed nothing for up to
six hours, which reads exactly like a broken updater.
And docs/REUSE.md was missing all of this: it covered Update URI, where to
instantiate the updater and making the repo public, but not the one rule that
is genuinely easy to get wrong.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
646d5e5cc1 |
Document the update smoke test and why the download address is rebuilt
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
0ac0e35787 |
1.4.1
The v1.4.0 zip that is already published contains the updater that trusts the repository's own browser_download_url — the one that reports a plain-HTTP raw IP. Anyone who installs 1.4.0 keeps that until an update arrives over exactly the address it gets wrong. It works today, because that address happens to be reachable, which is the reason to close it now rather than leave it working by luck. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
8d0fa8c9d2 |
Build the download address from the plugin header, not from the forge
The v1.4.0 release went out and the feed came back readable, with this in it:
"browser_download_url":
"http://57.129.89.117:25001/kw/woocommerce-email-discount-manager/..."
That field is filled from the forge's own configured root URL, which is not
necessarily the address the outside world reaches it on. A shop handed that
would be downloading plugin code over plain HTTP from a raw IP on a
non-standard port, bypassing the Cloudflare tunnel in front of gitea.nolimit.dk
and breaking the day that address changes.
parse_release() now rebuilds both the package and the release-page address from
the repository address in the plugin header, which is the one place that
already had to be right for any of this to work. tests/smoke.php pins it with
the exact response the live feed returned.
The release check had the same bug from the other end, and a worse version of
it: it verified the address the API reported rather than the one the plugin
builds, so it was a green check on a URL no shop ever uses. It now downloads
the package the plugin would download and opens the zip to confirm it is the
plugin and not an error page with a 200 on it.
And it only runs on the forge named in "Update URI". The other one is a mirror;
requiring a mirror to be anonymously readable failed the GitHub half of the
v1.4.0 release for a repository that is private on purpose.
ci/update-smoke.sh is the check none of the above can stand in for: install the
previous version into a throwaway shop and let WordPress find, download and
install the new one by itself. Every piece can be individually correct and the
update still not arrive.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwindandClaude Opus 5
|
4a5e3d8879 |
Run the text-domain check in a container when the runner has no PHP
The first Gitea run failed on `php: command not found`. GitHub's hosted runners ship PHP; the Gitea runner image does not, and the whole static job went red on one line after everything else in it had passed. ci_php() now uses the local php when there is one — a laptop, GitHub's runners — and a php:8.4-cli container otherwise. The repository goes in over a tarball and `docker cp` rather than a bind mount, because a Gitea Actions job runs inside a container talking to the HOST's docker daemon, so a host path there lands on an empty directory nobody created. Also: the include scan now says when it found nothing to check instead of reporting success. Running the suite with a deliberately crippled PATH showed it printing "0 plugin-relative include(s) checked" and then "green" — a check passing by checking nothing, which is the same failure the PHP lint step already guards against. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
d9a925ea75 |
Check the release runner has its tools before spending ten minutes
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
d8b2fe054c |
Read the update header once per request, not on every page load
The filter is registered on every request a shop serves, not just in wp-admin, and get_file_data() opens and scans the plugin file each time it is asked. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
kristianwindandClaude Opus 5
|
eca2851d35 |
Test against the newest WordPress and WooCommerce, and ship updates
Three things this repository could not do: prove the plugin still works on a
WordPress or WooCommerce released after it, get a fix onto a shop without
someone uploading a zip, and do either of those for the next plugin without
starting over.
ci/ is the test harness. ci/site-test.sh builds a throwaway WordPress +
WooCommerce in containers at any versions you name — including `nightly` and
`beta` — installs exactly the files the release zip will contain, and runs
tests/smoke.php inside it with wp eval-file. Real cart, real coupons, real
WC_Shipping_Rate objects: a mocked cart keeps passing after WooCommerce has
changed underneath it, which is the one failure worth catching here. WP_DEBUG
is on and any notice logged from this plugin's directory fails the build,
because that is the shape an upgrade actually breaks in — nothing fails, a
notice appears, and two releases later it is a fatal.
compat.yml runs that weekly against today's releases, the next WordPress and
the next WooCommerce, the oldest PHP the header promises and the newest PHP.
When it is green it opens a PR bumping "Tested up to" and "WC tested up to" —
only when green, because WooCommerce shows that second value to the shop owner
as an untested-plugin banner, and that banner is what they read before deciding
whether to press update.
includes/class-updater.php is the distribution half. It hooks
update_plugins_{hostname} for the host in the new "Update URI" header and reads
the Gitea release API, so WordPress handles the notice, the download, the
"Enable auto-updates" link and wp plugin update with no further code. Update
URI earns its place twice: since 5.8 a plugin that declares one is never asked
about on wordpress.org, so a .org plugin sharing this slug cannot be pushed
onto a shop running this one. The check sends nothing about the site and
overrides WordPress's default user agent, which carries the site's own URL.
release.yml tags, tests, builds, publishes — then reads the feed back with no
credentials. A private repository and a release with no zip attached both leave
a page that looks perfect to anyone logged in and an update no shop is ever
offered.
Measured before committing, all green: WP 7.1 + WC 11.1 on PHP 8.3 and 7.4,
WP 7.2-alpha on 8.3, and the beta cell falling back to stable on 8.4. No
deprecations from this plugin on any of them.
Three guards are there because the bug they catch is invisible without them:
the annotated tag is re-fetched before its message is read (checkout turns it
into a lightweight tag pointing at the merge commit), the two workflow roots
are kept in sync (.gitea/workflows hides .github/workflows entirely), and every
file the code loads must be in the release zip — which caught class-updater.php
being referenced and uncommitted while every local test passed.
docs/REUSE.md is the port to the next plugin: copy ci/, rewrite five lines.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
kristianwind
|
e4a40e53a0 | Initial commit: WooCommerce Email Discount Manager plugin |