Skip to content

Commit 4ced127

Browse files
committed
Merge remote-tracking branch 'origin/main' into claude/issue-triage-prioritization-24rqgv
# Conflicts: # CHANGELOG.md
2 parents d26cbb0 + 4b63cb5 commit 4ced127

197 files changed

Lines changed: 6035 additions & 511 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area":"cmd/mxcli","date":"2026-11-04","symptom":"`mxcli check --references` printed `✗ 1 reference error(s) found` and then `0 issues: 0 errors, 0 warnings, 0 info` — the reporter asked why a reference error does not count as an error (mendixlabs/mxcli#1726)","cause":"the closing summary sums the `printed` list, which only the `report` helper appends to; the reference tier prints its errors and warnings itself, so they never reached the total","file":"cmd/mxcli/cmd_check.go (reference tier appends to printed); test cmd/mxcli/check_reference_summary_test.go","insight":"When one summary is computed over a list that several tiers feed, a tier with its own print path drops out of the total silently. Only the run in the report had an earlier tier's violation, so the summary line printed at all; a script with nothing but a reference error printed no summary, which is why the test asserts `1 errors` rather than the absence of `0 errors`. Control: without the append, the test fails with no summary in the output.","refs":["ako/mxcli#1928","mendixlabs/mxcli#1726"]}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area":"cmd/mxcli","date":"2026-11-04","symptom":"The nightly goes red on the Mendix 11.14.0 leg only, in `TestTestAttach_KeepsTheHostingAppsPageBundles` (added the day before by ako/mxcli#1917): `mxcli test --attach` exits 1 with `this change needs a runtime restart (an entity or association changed), which --attach cannot do`, although the attach only adds a test microflow. 11.12.x, 11.13, 11.15 and 11.16 are green","cause":"On 11.14.0 every later build in an mxbuild --serve process fails, even with the model unchanged (`Cannot find module …/web/rollup.config.mjs`), and the failed /build response carries no restartRequired key at all. #1917 routes the attach's build through serveRecovery, whose legacy-hint path restarts onto a private serve and builds cold; a cold build reports restartRequired=true whatever changed, and runner_attach read that as a structural change. Before #1917 the same attach failed with the build failure itself, so attach never worked on 11.14.0; the test exposed it because its default 11.12.6 falls back to whatever mxbuild the nightly leg caches","file":"`cmd/mxcli/docker/serve_recovery.go` (rebuildFresh marks the cold answer `BuildResult.ColdRestart`; the incomplete-bundle path clears it when it takes the incremental answer), `cmd/mxcli/testrunner/runner_attach.go` (`attachRestartRefusal`), `cmd/mxcli/cmd_test_attach_bundle_integration_test.go` (11.14 branch)","insight":"A recovery that substitutes a fresh process's answer must say so: a cold build's restartRequired is \"unknown\", and only a caller that can restart may treat it as true. Settled by driving /build directly (a throwaway test with StartServe + Build, no watch loop): 11.14.0 build 2 with no change = Failure with no restartRequired; 11.15.0 = Success, false for no change and for a microflow, true for an entity, 0 pages (the 11.12.5 shape #1917 already recovers). That table is what puts the limit on 11.14.0 alone, so the test pins `>= 11.14 && < 11.15` and fails when an 11.14 mxbuild builds incrementally again. Reproduce in about 4 minutes: `mxcli setup mxbuild --version 11.14.0`, JAVA_HOME at a JDK 25, `MXCLI_RUNLIFE_VERSION=11.14.0 go test -tags integration -run TestTestAttach_KeepsTheHostingAppsPageBundles ./cmd/mxcli/`. Controls: the old test fails with the nightly's exact message; the new test passes on 11.14.0 and 11.15.0 and fails on 11.14.0 against a binary without the fix (it names the entity); stubbing the ColdRestart mark fails the two unit tests that pin it","refs":["mendixlabs/mxcli nightly run 41801646309","ako/mxcli nightly run 41801123003","ako/mxcli#1917","mendixlabs/mxcli#1723"],"test":"cmd/mxcli/cmd_test_attach_bundle_integration_test.go; cmd/mxcli/docker/serve_attached_test.go; cmd/mxcli/docker/serve_recovery_test.go; cmd/mxcli/testrunner/runner_attach_restart_test.go"}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area": "cmd/mxcli", "date": "2026-11-06", "symptom": "`mxcli git merge` on ManualResolutionRequired printed no property-level report at all when either side's mx diff failed (exit 129 on a constant whose ExportLevel was \"\" on one side and Hidden on the other), so a reader could not tell 'no details' from 'the diff crashed'", "cause": "The call site only called propertyReport when both diffs returned nil, with no else; propertyReport already rendered a missing file as '(diff unavailable: …)', but never saw the run's error", "file": "cmd/mxcli/cmd_git_merge.go (exit-2 branch, propertyReport)", "fix": "propertyReport takes each side's diff error (diffSide) and is always called: a failed side prints '(diff unavailable: <error on one line>)', the other side its changes", "insight": "A guard that skips output on any error turns one side's failure into silence about both; let the renderer own each side's failure. The mx diff crash itself reproduces on 11.14.0 (\"\" vs Hidden ExportLevel: exit 129), see ako/mxcli#1980", "refs": "ako/mxcli#1981, mendixlabs/mxcli#1750", "test": "cmd/mxcli/gitmerge_test.go (TestGitMerge_FailedDiffIsReportedNotSkipped)"}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area": "cmd/mxcli", "date": "2026-11-06", "symptom": "mendixlabs/mxcli#1754: `marketplace install` of a protected (add-on) module shipped as .mxmodule (Menditect MtaPluginModule 11.5.5, Marketplace 214717) failed with \"file is not a database\"; `mx module-import` refuses such a package outright (\"Importing protected module is not supported\", exit 111).", "cause": "The package's project.mpr is not an SQLite .mpr but one BSON document {_ProductVersion, Contents} holding the project as a single tree with every unit nested in its container, so every reader that expected SQLite failed and mx has no import for it.", "file": "cmd/mxcli/marketplace/moduletree.go (split the tree into units at Folders/Documents/DomainModel/ModuleSettings/ModuleSecurity of modules and folders; write them with AddRawUnit; write the declared package files beside the reference; refuse a tree newer than the project), cmd/mxcli/marketplace/scratch.go (PackageProject takes that path for a tree)", "insight": "Replacing `mx module-import` means replacing everything it does, not just the unit write: it also writes the package's declared files next to the .mpr and converts the module to the project's Mendix version. The first cut of mendixlabs/mxcli#1755 did only the units, which installs fine (install copies files from the .mpk) but gives `marketplace diff`/`update` a reference without javasource/javascriptsource — the #1441 'every action changed locally' failure again — and units in the package's schema. Ask which readers consume the reference (refcache.go isModelFile lists them), not only which writer produced it. The unit test asserts Start.java beside the reference, which only the InstallPackageFiles call writes; the conversion is not reproduced (no mx), only a newer tree is refused.", "refs": ["mendixlabs/mxcli#1754", "mendixlabs/mxcli#1755", "mendixlabs/mxcli#1441"], "test": "cmd/mxcli/marketplace/moduletree_test.go"}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area": "mdl/backend", "date": "2026-11-06", "symptom": "`create constant` stored ExportLevel \"\" where Studio Pro writes \"Hidden\"; mx check accepted it, but mx diff of that unit against a \"Hidden\" copy on another branch crashed (exit 129, Value cannot be null. (Parameter 'element')) and git merge lost its property report; `create or modify constant` also turned a stored API/Hidden into \"\"", "cause": "constToGen wrote c.ExportLevel verbatim, and constants have no MDL spelling for it, so the executor's model always carried \"\"; UpdateConstant was the one rewrite path not routed through keepStoredExportLevel, and so missing from TestUpdatePaths_KeepStoredExportLevel's enumeration", "file": "mdl/backend/modelsdk/constant_write.go (constToGen, UpdateConstant)", "fix": "constToGen defaults to \"Hidden\" (orDefault, as every other writer); UpdateConstant keeps the stored level via keepStoredExportLevel, which ignores a stored \"\" and so also repairs units an earlier version wrote", "insight": "An enum value mx check accepts can still break Mendix's own tooling: measure the consumer that fails (mx diff of a \"\" copy against a \"Hidden\" copy: 129; two \"Hidden\" copies: 0), not just the build. When a carry helper is enumerated by a table test, a writer missing from the table is the bug — grep the writers for SetExportLevel without orDefault", "refs": "ako/mxcli#1980, mendixlabs/mxcli#1749", "test": "mdl/backend/modelsdk/issue816_export_level_test.go (Constant case, TestConstant_ExportLevelDefaultsToHidden); mdl-examples/bug-tests/1980-constant-export-level-hidden.mdl"}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area": "mdl/backend", "date": "2026-11-06", "symptom": "alter workflow: `drop X outcome 'V'` / `drop X outcome <enum value>` dropped the first of two outcomes sharing that value; `drop X boundary event` could not say which of several events, so under mdl 1 it was refused with no way to drop the second; check-time guards went silent on a reference the mutator resolved by name, because resolveStoredActivity pooled a jump captioned with its target's name with the target itself", "cause": "Both mutators' drop loops stopped at the first match and never counted; the boundary-event op carried no address at all; the executor's resolveStoredActivity copied findActivityByCaption but not its preferNameMatches narrowing", "file": "mdl/backend/wfmutator/mutator.go (dropOneOutcome), mdl/backend/mcp/workflow.go (dropFromActivityArray), mdl/backend/workflow_members.go (BoundaryEventIndex), mdl/executor/validate_workflow_activity_kind.go (resolveStoredActivity)", "fix": "A value that matches more than one outcome is refused as ambiguous, nothing written, in both mutators; `boundary event N` (1-based, describe order) addresses one event, out of range refused at exec before the mutator; resolveStoredActivity prefers Name matches without @N", "insight": "A check-time resolver that mirrors a mutator must mirror every narrowing step, or the check silently abstains (it returns nil on ambiguity by design) exactly where exec acts; test the resolver on the jump-caption shape directly. A drop loop with `!found` guards is the tell for a first-match guess: count matches, then decide", "refs": "ako/mxcli#808, ako/mxcli#796", "test": "mdl/backend/wfmutator/mutator_test.go (DuplicateValueRefused, DropBoundaryEvent_ByIndex); mdl/executor/alter_workflow_member_address_test.go (DropBoundaryEventByIndex, ResolveStoredActivity_PrefersName); mdl-examples/bug-tests/808-drop-boundary-event-by-number.mdl"}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area":"mdl/executor","date":"2026-11-04","symptom":"`check --references` passed drop/rename/move of a document that does not exist, and alter enumeration / alter microflow on one, while exec refused each with `<kind> not found` — 9 of the 11 statement forms that name an existing document (only alter entity and alter page were resolved)","cause":"validateAlterTarget was written for ALTER and extended one statement at a time; the drop/rename/move statements resolve against the same listings but were never routed to it","file":"mdl/executor/validate_alter_target.go (validateAlterTarget, targetListing, checkTarget, moveTargetKind), mdl/executor/validate.go (collectSingle: indirectDocs, renamedModules, opaqueModules, opaqueScript); test cmd/mxcli/check_statement_target_test.go","insight":"The risk in widening a not-found check is the false refusal, not the miss: a document can reach a name without a create statement naming it — an earlier rename or move, a rename module, an execute script, a generated SQL connector, a business event service, a bulk external-entities import. Record each in the pre-pass and stay silent for that name or module; the check must stay quieter than exec. Matching is exact-case because exec's lookups are. A PedApp test per form, each with an existing-target control, plus if-exists / created / renamed / moved controls. Control: without the new cases all 13 forms pass check.","refs":["ako/mxcli#1821","ako/mxcli#555"]}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area":"mdl/executor","date":"2026-11-04","symptom":"`textbox (Attribute: PlannedOn)` in a data view, or `ContentParams: ({1} = PlannedOn)` / `CaptionParams`, on an entity without that attribute: check --references passed, exec wrote it, mxbuild CE1613 \"The selected attribute 'M.E.PlannedOn' no longer exists\" — measured 3 of 3 on a fresh 11.12.6 app, control page clean","cause":"the input-widget scope walk (checkInputBinding) looked the attribute up and returned silently when it was not found unless the name was an association; template parameters were never looked up","file":"mdl/executor/validate_widget_attribute_type.go (reportMissingAttribute, checkTemplateParams), mdl/executor/validate_widget_attribute_scope.go (walk); test cmd/mxcli/check_widget_attribute_exists_test.go","insight":"The context walk, the member index with inheritance and the association hops were already there for the type rule (MDL-WIDGET39) — the not-found case was a silent `return` in it. Before writing a new resolver, grep for the lookup that already returns found/known and see what it does on a miss. Stay quiet where the index is not sure: an unknown chain (known=false), an unresolved context, an altered entity, an expression or $var path, and the audit members (createdDate/changedDate/owner/changedBy), which bind by name but are not in the attribute list. Control: without the two calls the textbox and content-parameter subtests pass check.","refs":["ako/mxcli#555"]}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area": "mdl/executor", "date": "2026-11-04", "symptom": "`mxcli check --references` passed `Image: 'Atlas_Core.Content.mendix'` for the stored image `Mendix` (and `Atlas_Core.content.Mendix`, `atlas_core.Content.Mendix`); mx then reported CE1613 \"The selected image '…' no longer exists\" for each. The miss hint `it holds: mendix` printed the name lower-cased, so copying it from the message produced the CE1613", "cause": "imageRefErrors / buildImageQualifiedNames (and the script context's created collections) keyed every image and collection lower-cased on the unmeasured assumption, pinned by two tests, that Mendix resolves names case-insensitively", "file": "`mdl/executor/validate_widget_image_ref.go` (imageRefErrors, sameNameOtherCase, imagesInCollection, buildImageQualifiedNames), `mdl/executor/validate.go` (scriptContext image collections)", "insight": "Measure case-sensitivity per part before encoding it: one blank-app run with four pages (exact, wrong image case, wrong collection case, wrong module case) through `docker check --no-update-widgets` settled it — CE1613 on all three, clean on the exact one. Two tests asserted the opposite (\"Mendix resolves names case-insensitively, and so must this\") with no measurement behind them; they were inverted, not deleted. A case-only miss names the stored spelling instead of the generic hint, and the hint lists names as stored. The icon reference check (iconIndex) was already exact. Found while verifying ako/mxcli#1503. The navigation `app icon` goes through the same resolveImageRefs and carried the same assumption (TestAppIconMustResolveAtExec accepted `myfirstmodule.images.logo`): measured, main wrote `app icon Atlas_Core.Content.mendix` and mx reported CE1613 at the navigation profile, so that case is now refused too. A full `make ci-local` needs the testdata/testapp submodule (`git submodule update --init testdata/testapp`); without it TestIssue1640_RegisteredListMarkersAreWhatStudioProStores fails on main as well", "refs": ["ako/mxcli#1503"], "ce": ["CE1613"]}
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"area":"mdl/executor","date":"2026-11-04","symptom":"`alter page M.P { add parameters $X: … }` then a show page passing X, in one script: check --references and exec refused it with `page M.P has no parameter \"X\"`; the same statements as two scripts ran (mendixlabs/mxcli#1736)","cause":"the script pre-pass recorded page parameter names only from create page, so for an altered page the show page argument check fell through to the stored parameter list","file":"mdl/executor/validate.go (collectDefinitions AlterPageStmt case, pageParamEdits), mdl/executor/validate_show_page_params.go (recordPageParamEdits, applyPageParamEdits); test validate_show_page_params_alter_test.go","insight":"A script-context index that only listens to create statements reads every alter as a no-op — the same class as the #1355 script-set fix, one level down. Record the alter's edits rather than a computed list, because the pre-pass has no project to read the stored list from; apply them over whichever list wins at lookup time. End-to-end on PedApp 11.13.0: the base build refuses with the reported message, the fix passes check and exec writes both. Control: without the pre-pass case, the add/drop/create-then-alter subtests fail.","refs":["ako/mxcli#1940","mendixlabs/mxcli#1736"]}

0 commit comments

Comments
 (0)