|
158 | 158 | {"area": "cmd/mxcli", "date": "2026-10-03", "symptom": "`mxcli report` could not score a project's own modules: `lint` has --modules, `report` had only --exclude", "cause": "Feature gap; and the LintContext module filter alone would not make the score exact, because project-level findings (CONV008 role mappings, project security) carry no module and are reported regardless", "file": "`cmd/mxcli/cmd_report.go`, `mdl/linter/report.go` (`ScopeToModules`, Report.Modules)", "insight": "Filter the scored violations to those located in a selected module, and print the selection in every format so a module score is not mistaken for the project's", "refs": ["ako/mxcli#953"]} |
159 | 159 | {"area": "cmd/mxcli/docker", "date": "2026-10-03", "symptom": "`mxcli docker build` (and docker run / reload, which call it) rewrote an MPRv1 project's .mpr, rewrote every MPRv2 .mxunit (restored with new mtimes), and wrote theme-cache/, deployment/, javasource/ proxies, the .launch file, .classpath and .project into the project; the TUI checker and `mxcli eval`'s mx_check wrote theme-cache/web/ and deployment/sass/ on every run", "cause": "update-widgets ran on the project under a snapshot that restored only v2 storage, and mx check / MxBuild ran on the project itself; the TUI and eval runner ran a bare `mx check <project>`", "file": "`cmd/mxcli/docker/build.go` (`buildOnCopy`), `cmd/mxcli/docker/check.go` (`MxCheckOnCopy`), `cmd/mxcli/tui/checker.go` (`runMxCheck`), `cmd/mxcli/evalrunner/checks.go` (`checkMxCheck`)", "insight": "Run update-widgets, mx check and MxBuild on one temporary copy (copyProjectToTemp) and write only the output directory. Measured on the 11.14 testapp: the PAD from the copy differs from the in-place build in the same 9 files as two in-place builds of identical copies differ (cache-bust stamps, operation ids, the native metro paths), so the output is equivalent; rebuild time unchanged (58s vs 59s), because a PAD build gains nothing from the project's deployment/. 11.14's blank app needs JDK 25, so the real-mx build test skips without it; run it with 11.13's mx.", "refs": ["ako/mxcli#961", "ako/mxcli#951", "mendixlabs/mxcli#808"]} |
160 | 160 | {"area": "cmd/mxcli", "date": "2026-10-03", "symptom": "ako/mxcli#962 item 3: in VS Code, two calls to a stored void JavaScript action with the same output name (Studio Pro's `$ReturnValueName`/`$RefreshEntity` shape) are squiggled MDL063, while `mxcli check -p` passes them", "cause": "runSemanticValidation called executor.ValidateMicroflow/ValidateNanoflow, which pass a nil void-action resolver: without the project every call output counts as a declaration", "file": "`cmd/mxcli/lsp_diagnostics.go` (runSemanticValidation); `mdl/executor/validate_void_code_calls.go` (FlowRules, CodeActionCache)", "fix": "executor.NewFlowRules(prog, s.findMprPath(), s.codeActions): resolves actions through the script and the workspace project (opened lazily), treats an unresolvable action as possibly void (unknownIsVoid) for MDL063 but never for MDL093, and shares project answers across keystrokes for 30s since one action read costs ~300ms on PedApp", "insight": "An entry point that wraps a richer internal API with nil arguments (ValidateMicroflow = validateMicroflowWith(stmt, nil)) silently gives every caller the weakest behaviour; a fix landed in the richer API (#958) does not reach them. Grep the exported wrapper's callers when the internal one gains a parameter. Measure the cost before putting project I/O on a keystroke path", "test": "`cmd/mxcli/lsp_void_calls_test.go` (PedApp: void pair clean with and without project, Boolean pair control, MDL093 only with project); `mdl/executor/validate_void_code_calls_test.go` (TestCodeActionCache_SharesProjectAnswersAcrossRuns)"} |
| 161 | +{"area": "cmd/mxcli", "date": "2026-10-04", "symptom": "`run --local --watch` (Mendix <= 11.13, rollup bundler): after a while every page change fails with `web client rebuild failed: web client watcher exited` (or `client bundle not served after apply: web client re-bundle: web client build timed out after 5m0s`) and nothing reaches the browser until `run --local` is restarted; after adding an entity the next changes fail with `ENOTDIR: not a directory, stat '.../web/pages/<Page>.js/package.json'`", "cause": "watchAndApply held a bare *WebClientWatcher: (1) once it exited nothing restarted it (only recoverMissingPages did), so WaitForRebuild failed every later change; (2) a failed incremental build (rollup's commonjs resolver hitting web/pages mid-rewrite by the serve build) left the watcher erroring and the change was dropped; (3) ensureClientServed's recovery ran a one-shot NODE_ENV=production BuildWebClient in the same web/ dir while the watcher was still running — two rollups on web/dist; (4) the 5m limit was hard-coded and a timeout printed nothing about why", "file": "cmd/mxcli/docker/webclient_supervisor.go, cmd/mxcli/docker/runlocal.go (watchAndApply, ensureClientServed), cmd/mxcli/docker/webclient.go (webClientTimeout, webClientBuildLogTail)", "fix": "bundlerSupervisor owns the bundler: EnsureAlive restarts an exited one (backoff 2s..60s after failed starts), AwaitRebuild retries a failed/aborted incremental rebuild once with a fresh bundler, Rebundle = stop+reap then start (never two). ensureClientServed takes the rebundle func; clientRebundler hands it the supervisor under --watch and the one-shot otherwise. --web-client-timeout / MXCLI_WEB_CLIENT_TIMEOUT; timeout errors append the last 30 lines of deployment/log/web-client-build.log. sessionNotice prints that a restart dropped sessions", "insight": "Killing the runner (`kill <node rollup-runner.mjs pid>`) reproduces the dead-watcher state in seconds — no need to wait for it to die on its own. A fresh bundler is the universal recovery under --watch: its first build is a full bundle of the current source, so it covers missing pages, dangling chunks, a dist/ deleted by Gradle, and a transient incremental failure alike, without a second process on web/dist. Note: exec.Cmd.Wait called a second time concurrently with the reaper did block until exit on this Go version, so the old Stop was not the overlap — the one-shot in ensureClientServed was", "test": "cmd/mxcli/docker/webclient_supervisor_test.go (TestBundlerSupervisor_RestartsExitedBundler, _AwaitRebuildRecovers, _RebundleNeverOverlaps, TestEnsureClientServed_WatchModeRebundleIsExclusive, TestBuildWebClient_TimeoutShowsLogTail); live: 11.13 scratch app, 7 consecutive changes incl. a killed runner"} |
| 162 | +{"area": "cmd/mxcli", "date": "2026-10-04", "symptom": "`run --local --watch`: an `mxcli exec` (or save) made while a change is still building/applying is never built — no `Change detected` follows, the app keeps the previous model, and re-running the script writes nothing (byte-idempotent) so nothing re-triggers", "cause": "watchAndApply set `last = sourceMTime(...)` after every successful apply, under a comment claiming it kept mid-build edits; it did the opposite — the edit's mtime was folded into the baseline, so the next tick saw nothing newer", "file": "cmd/mxcli/docker/runlocal.go (watchAndApply)", "fix": "keep `last` at the settled mtime the build was taken from; the build writes nothing under the watched model/theme source (checked with find -newer during a live run), so this cannot self-trigger", "insight": "Found while reproducing #971 with a script that waited for the first output line of a change instead of its `applied` line — the next exec landed during a 2-minute restart-apply and vanished. Any test of a watch loop should include an edit made DURING a build, not only between builds", "test": "live only (11.13 scratch app, hsqldb): exec an entity add, exec a page change 15s into its build; fixed binary builds it as the next build, the binary with the refresh restored shows no further build after 45s"} |
| 163 | +{"area": "cmd/mxcli", "date": "2026-10-04", "symptom": "ako/mxcli#970 item 2: `theme create --from design.css` with only a :root block (no dark block) wrote the design's light --mxt-ground/--mxt-ink/--mxt-brand into the base theme's dark mixin, whose other surfaces stayed dark; the first injected token also sat on the `@mixin … {` line, unindented", "cause": "Tokens.forVariant returned the base declarations for EITHER variant, and seedTokens applied it to the alt-palette mixin unconditionally; applyTokens matched `(?m)^(\\s*)name`, and \\s* at ^ swallows the preceding newline (and blank line), so the replacement lost its line break and indent", "file": "`cmd/mxcli/theme/create.go` (seedTokens, Create/CreateResult.UnseededVariant); `cmd/mxcli/theme/tokens.go` (applyTokens, Tokens.declares); `cmd/mxcli/cmd_theme.go` (note)", "fix": "seed the alt mixin only when the design declared a block for that variant; otherwise leave it byte-identical to the base and report UnseededVariant, which the CLI prints as a note; match the indent with [ \\t]* instead of \\s*", "insight": "A base palette is the default variant's palette, not 'both': a token set that does not say which variant it describes must not seed the other one. And under (?m), ^\\s* is not 'leading indentation' — it crosses lines; use [ \\t]*. The control for 'mixin untouched' is the same scaffold with no design at all, compared byte for byte", "test": "`cmd/mxcli/theme/create_variant_test.go` (all three bases, base-only vs variant block, indentation); `cmd/mxcli/cmd_theme_test.go` (TestThemeCreate_NotesTheVariantABaseOnlyDesignDidNotSeed)"} |
0 commit comments