saropa_lints 15.0.3

2134 custom lint rules with 254 quick fixes for Flutter and Dart. Static analysis for security, accessibility, and performance.

Changelog

                                    ....
                             -+shdmNMMMMNmdhs+-
                          -odMMMNyo/-..``.++:+o+/-
                       /dMMMMMM/               `````
                      dMMMMMMMMNdhhhdddmmmNmmddhs+-
                      /MMMMMMMMMMMMMMMMMMMMMMMMMMMMMNh/
                    . :sdmNNNNMMMMMNNNMMMMMMMMMMMMMMMMm+
                    o     ..~~~::~+==+~:/+sdNMMMMMMMMMMMo
                    m                        .+NMMMMMMMMMN
                    m+                         :MMMMMMMMMm
                    /N:                        :MMMMMMMMM/
                     oNs.                    +NMMMMMMMMo
                      :dNy/.              ./smMMMMMMMMm:
                       /dMNmhyso+++oosydNNMMMMMMMMMd/
                          .odMMMMMMMMMMMMMMMMMMMMdo-
                             -+shdNNMMMMNNdhs+-
                                     ``

Made by Saropa. All rights reserved.

Learn more at https://saropa.com, or mailto://[e-mail]

2100+ custom lint rules with 250+ quick fixes for Flutter and Dart — static analysis for security, accessibility, performance, and library-specific patterns. Includes a VS Code extension with Package Vibrancy scoring.

Package — pub.dev/packages/saropa_lints

Releases — github.com/saropa/saropa_lints/releases

VS Code Marketplace — marketplace.visualstudio.com/items?itemName=saropa.saropa-lints

Open VSX Registry — open-vsx.org/extension/saropa/saropa-lints

---

15.0.3

The scan CLI now lets users filter diagnostics by severity, so AI agents and CI pipelines can suppress info-level noise and focus on warnings and errors. The extension also stops losing the in-editor analyzer plugin when Lint integration is switched off and back on, and now reports that plugin's real state instead of implying it from a setting that does not control it. log

Added

• --min-severity flag for the scan command filters diagnostics by severity threshold — --min-severity warning excludes info-level output from both stdout and the report file, reducing noise for AI agents and CI pipelines. No action required.
• --max-severity flag for the scan command caps output at a severity ceiling — --max-severity warning hides errors so you can triage lower-priority noise in isolation. No action required.

Added (Extension)

• When Lint integration and the analyzer plugin disagree in a way you probably did not intend — scan-on-save on with in-editor diagnostics silently off, or the multi-gigabyte plugin still loading while lints read as off — the extension now offers once to reconcile it either way. Answer or dismiss it and it does not ask again for that project.

Fixed (Extension)

• Clicking a finding in the Problems panel now highlights the full diagnostic span instead of a single character — eliminates the "highlight every matching letter" noise caused by VS Code's occurrence-highlight when the range was only one character wide. No action required.
• Turning Lint integration off and then on again left the in-editor analyzer plugin switched off — the off step comments out the plugins: block in analysis_options.yaml, and the on step never put it back, so a project silently lost live diagnostics with no indication of why. Enable now restores the block when it was this extension's own Off that commented it out, leaving new projects (which default to the lighter scan-on-save delivery) untouched. This has proven to be tricky!
• The sidebar now reports the analyzer plugin's actual on-disk state as its own row, so "Lint integration: On" can no longer sit above a project whose plugins: block is commented out — clicking that row while it reads Off restores the plugin. No action required.
• The record of which side switched the analyzer plugin off is now stored twice, so a VS Code profile switch or extension-storage reset can no longer make Enable silently stop restoring the plugin. No action required.
• The analyzer plugin row and its restore logic now track every folder in a multi-root window and start working in a window that had no folder open at startup, instead of only the one folder present when the extension activated. No action required.
• Changing the tier froze the whole window until the config rewrite finished, behind a notification that showed one static title and no Cancel button — on a large project that is indistinguishable from a hang. The tier change now runs in the background with a live elapsed-time counter and a working Cancel, joins a second invocation to the one already running instead of racing on the same file, and restores the previous tier setting if the change does not complete. No action required.

Maintenance

• (Extension) Added explicit "types" field to both tsconfig.json and tsconfig.test.json so the TypeScript compiler reliably resolves Node.js globals and test framework types instead of relying on auto-discovery. No action required.
• (Extension) Added verify-tsconfig-types build gate that validates both tsconfig files during precompile — fails when an imported @types/* package is missing from either config's "types" array. No action required.
• (Extension) Pinned Filipino translation of "Analyzer plugin" in the curated dictionary so the MT pipeline stops overwriting it with untranslated English on every run. No action required.
• (Extension) The i18n pipeline now warns at the start of every run when a curated dictionary key no longer matches any English source string — catches silent regressions where a renamed en.json string causes the dictionary entry to stop matching and MT takes over. Pass --fail-on-drift to hard-gate (added to publish pipeline). No action required.
• (Extension) Fixed 9 orphaned curated dictionary keys across nl, fr, ur, bn, fil, and he — stale from prior en.json renames ("Search Packages" → "Search packages", "Open Lints Config" → "Manage Rule Packs"). No action required.
• Added fixture coverage for avoid_positioned_outside_stack — covers the Positioned-in-list-passed-to-custom-widget false positive that was already fixed in v4.13.0 but had no test. No action required.

---

15.0.2

This release focuses on improving the reliability and user experience of the extension's setup workflows. Progress notifications now provide real-time feedback during lengthy operations to clearly communicate the current status. Safeguards have also been introduced to prevent duplicate, conflicting tasks from executing concurrently if a command is triggered multiple times. log

Fixed (Extension)

• The "Enabling Saropa Lints" progress notification stayed on a single static title for the entire pub get step, which can take over a minute on projects with many plugins — with nothing on screen to distinguish "still working" from "stuck," clicking Cancel (or clicking "Enable" again) mid-run was a reasonable reaction. The notification now shows which step is running and a live elapsed-time counter (e.g. "Running pub get… (45s)"). No action required.
• Clicking "Enable" again while an enable flow was already running started a second, fully concurrent flow — both writing pubspec.yaml/analysis_options.yaml and shelling out to pub get/write_config at the same time — instead of joining the one already in progress, which could stack duplicate progress notifications and race on the same files. A second call now joins the in-flight run instead of starting a new one. The same fix applies to "Create Baseline" (saropa_baseline.json), which had the same gap. No action required.

---

15.0.1

Version 15.0.1 improves the editor extension's responsiveness and resolves a file-parsing bug that prevented the plugin from re-enabling. The setup flow now executes asynchronously to prevent UI freezes, while deactivated lint configurations generate significantly smaller files by omitting unused inline documentation. log

Fixed (Extension)

• A project whose plugins: block is written commented-out (new projects, or one where "Turn Off Lint Integration" was used) no longer gets the full per-rule description dump on every regenerate — the disabled block now keeps only the rule_name: true/false lines needed to restore the exact configured tier, dropping the multi-hundred-line prose and box-drawing headers that served no purpose while inert. A live (uncommented) block is unaffected and keeps its full inline documentation. No action required; re-run dart run saropa_lints:init or trigger a config write to see the smaller file.
• "Enabling Saropa Lints" could appear to hang forever on larger projects — the enable flow ran pub get, config write, and analysis synchronously, freezing the whole editor for as long as those took instead of just showing progress. The flow now runs them without blocking the UI and can be canceled from the progress notification. Canceling during the final analysis step also no longer silently reports "Enable" as successful — it now stops and logs the cancellation instead of turning the plugin on as if the flow had completed. No action required.
• "Re-enable Plugin" could report "nothing to restore" on a project whose analysis_options.yaml mixed CRLF and plain-LF line endings, even though the disabled plugins: block was plainly present — line detection now tolerates mixed endings instead of assuming one for the whole file. No action required.

---

15.0.0

Version 15.0.0 adds new quick fixes for error logging and variable placement while introducing a persistent background daemon for significantly faster IDE save-scans. This release resolves false positives across exception handling, lifecycle timers, static method detection, and platform target checks. Project tier management is now unified directly through project configuration, reducing default editor memory overhead. log

Added

• require_error_logging now offers a quick fix: applying it inserts a debugPrint call logging the caught error (interpolating the captured exception variable when one exists, or naming the statically-known exception type when it does not) instead of only reporting the missing log call.
• move_variable_closer_to_its_usage now offers a quick fix: applying it moves the flagged declaration down to just before its first use. The fix only activates when doing so is provably safe (a single-variable declaration whose initializer shares no identifier with any statement it would move past) and otherwise leaves the diagnostic for manual review, so no action is required beyond reviewing the proposed edit before applying it.

Fixed

• avoid_catching_generic_exception no longer flags on Object/on Exception/dynamic catch clauses whose body forwards the caught error to a logging or crash-reporting call (or rethrows it) before falling back — this is a deliberate pattern for also catching Error subtypes and reporting them, not a swallowed exception. Untyped catch (e) is unaffected. (plans/history/2026.08/2026.08.15/avoid_catching_generic_exception_false_positive_logged_broad_catch.md)
• require_error_boundary no longer flags a MaterialApp/CupertinoApp built inside main()'s own catch clause when that clause already logged the caught error and its try body attempted runApp(...) — that's the app's crash-recovery fallback screen, not its normal entry point, and demanding it also carry an error-boundary builder: is recursive. The same shape outside main(), without logging, or without an runApp attempt in the try body still requires a builder: as before. (plans/history/2026.08/2026.08.15/require_error_boundary_false_positive_fallback_ui_inside_catch.md)
• require_error_logging no longer flags a catch/on Type clause with no captured exception variable if its body still calls a recognized logging function — a static message like on TimeoutException { debug('timed out'); } is a complete log entry even without touching the exception object. A clause with no captured variable and no logging call is still flagged, as before. (plans/history/2026.08/2026.08.15/require_error_logging_false_positive_unparamed_catch_with_logged_body.md)
• require_app_lifecycle_handling, avoid_work_in_paused_state, and require_lifecycle_observer no longer flag a Timer/Stream.periodic/.listen() subscription that is created and canceled/closed within the same State class's own initState/dispose() pair — that's Flutter's standard cleanup contract for a foreground-only ticker that doesn't need to pause on backgrounding, since it stops existing when the widget is disposed. A class whose dispose() does not cancel the field it created, or that assigns the Timer/subscription somewhere dispose() can't prove cleanup for, is still flagged, as before. (plans/history/2026.08/2026.08.15/require_app_lifecycle_handling_false_positive_dispose_cancels_timer.md)
• require_ios_deployment_target_consistency no longer flags import 'dart:async' (or any other import/export URI) as Swift async/await usage — the rule now skips string literals inside import/export directives before checking them against its tracked iOS 15+ API names. A genuine API name appearing elsewhere in the file is still flagged, as before. The same import/export-URI substring-match false positive was also fixed in require_ios_live_activities_setup (triggered by import 'package:live_activities/...') and require_ios_certificate_pinning (triggered by package import paths containing segments like /auth). (plans/history/2026.08/2026.08.15/require_ios_deployment_target_consistency_false_positive_import_uri_misattribution.md)
• prefer_static_method no longer flags methods that read instance fields or call instance methods via bare (unprefixed) identifiers — the idiomatic Dart style used throughout most codebases. Previously the rule only recognized an explicit this. prefix, so any method touching instance state through a bare identifier (including inside a nested closure) was misdiagnosed as "could be static." A method that truly uses no instance state anywhere is still flagged, as before. (plans/history/2026.08/2026.08.15/prefer_static_method_false_positive_implicit_field_access.md)
• move_variable_closer_to_its_usage no longer flags a deliberate "load N values, then consume all N in the same order" batch shape (e.g. five sequential await-loads followed by five field assignments) — a sibling declaration in the same contiguous run that is itself genuinely used elsewhere, or the first-use site of another such sibling, no longer counts toward the "unrelated intervening statements" distance. A genuinely far-apart single declaration, declarations used out of matching order, or unused padding declarations sitting next to a real one, are all still flagged, as before. (plans/history/2026.08/2026.08.15/move_variable_closer_to_its_usage_false_positive_batch_declaration_grouping.md)
• require_firebase_app_check_production and require_firebase_app_check no longer flag Firebase.initializeApp() when FirebaseAppCheck/AppCheck activation is deferred to a separate, actually-called function elsewhere in the same file — a common pattern for keeping a slow/flaky Play Integrity check off the startup path. A file where App Check is only mentioned in a comment, or where the activating function exists but is never called from anywhere, is still flagged, as before. (plans/history/2026.08/2026.08.15/require_firebase_app_check_production_false_positive_activation_in_separate_function.md)
• require_log_level_for_production no longer flags a bare verbose-log call (e.g. debug(...)) when the called function's own log-level parameter (level, logLevel, severity, or verbosity) already defaults to a safe value — demanding an explicit level: argument in that case would be a no-op. A callee whose default is itself verbose, unrecognized (numeric or constructor-call), or unresolvable, is still flagged, as before. (plans/history/2026.08/2026.08.15/require_log_level_for_production_false_positive_default_level_param.md)

Changed (Extension)

• Saving a Dart file now scans it in an external process and shows findings as squiggles and Problems panel entries — no separate setting to find or enable, this is what saropaLints.enabled now does. Turning that toggle off stops save scans and shuts the scanner down immediately, rather than leaving stale findings in the Problems panel. saropaLints.scanOnSave.resolveTypes (default on) controls whether scans fully resolve types so type-based rules fire; turn it off only if save latency matters more than catching those rules.
• Type-resolved save scans run through a persistent scan_daemon process that builds the analyzer's project context once and keeps it warm, so a save is checked in a few seconds instead of re-paying a roughly one-minute analyzer warmup on every save. The status bar shows a warming message while the first scan after opening is still resolving; the daemon restarts automatically (with backoff) if it stops. Measured memory is comparable to the in-process analyzer plugin — the daemon's advantage is living outside the editor's own process, not a smaller footprint.
• New projects (dart run saropa_lints:init or the extension's Enable) no longer get a live in-process analyzer plugin — the plugins: block is written commented out by default, since it can hold several GB of resolved analysis state on large projects for no benefit over the scan-on-save daemon above. A project that already had the plugin running, or had it explicitly turned off, keeps that state through tier changes and re-enabling; uncomment the block in analysis_options.yaml to opt back in to live in-editor squiggles, or run the new "Saropa Lints: Re-enable In-Process Plugin" command to do it in one step (it also restarts the Dart analysis server so the plugin reloads immediately).
• New command "Saropa Lints: Scan Whole Project for Issues" runs a cancelable whole-project scan so files you haven't saved this session still show up in the Problems panel — save-triggered scanning alone only checks a file once you save it. It streams results in chunks as it goes and can be canceled mid-scan from the progress notification; run it from the Command Palette when you want full coverage, not automatically on open (a full pass on a large project can take tens of minutes).
• A save-triggered scan of a single file no longer prints a misleading progress bar estimating its position against the whole project (e.g. "Files: 1/4477, ETA: 2h"). That estimate now only appears during the long-lived in-editor plugin session it was designed for; one-shot scans (save-triggered daemon, scan CLI) show a plain file count instead.
• analysis_options.yaml is now the single source of truth for a project's lint tier. Save-triggered scans, the whole-project baseline scan, and the tier picker's "current tier" display now read the tier straight from analysis_options.yaml instead of trusting the (possibly stale) saropaLints.tier setting, so a hand-edited or regenerated config file can no longer silently disagree with what the extension shows or scans with. SAROPA_TIER remains available as a dev-only override but now logs a warning when it disagrees with the project's own config; saropa_tier: in analysis_options_custom.yaml is deprecated in favor of analysis_options.yaml.

Maintenance

• Investigated a no_magic_string false-positive report (string literal inside a //-commented-out debugPrint call) and confirmed by code inspection it cannot occur — the rule and all its gating helpers are AST-callback-only, with no raw-text scanning. Added a resolved-analyzer regression test pinning this behavior. (bugs/no_magic_string_false_positive_commented_out_code.md)
• Manually corrected seven German and Swahili extension strings that had shipped corrupted machine-translation output — a mangled literal --resolve CLI flag, two entries collapsed into a repetition loop (one leaking a fragment resembling a stray prompt artifact), and grammatically broken fallback text — and added each as a curated dictionaries.py override so a future translation run can never regenerate the same corruption from cache.

---

14.5.9

This release adds a rule catching a common button-labeling mistake: cramming extra detail into a button's main text using parentheses instead of the dedicated subtitle line. It also closes the last gap in the "Lint integration off" toggle: the analyzer plugin itself now refuses to enable any rules while the integration is disabled, so no fallback configuration can silently re-enable analysis and its multi-gigabyte memory footprint. log

Added

• New rule avoid_parenthesized_button_caption (Comprehensive tier): flags CommonButton / CommonButtonWait calls where the text: parameter contains parenthesized text that belongs in subtitleText: instead. No action required.

Fixed

• The analyzer plugin now enables zero rules whenever "Lint integration" is toggled off, even if it gets loaded anyway — previously fallback configuration could re-enable over a thousand rules and hold several GB of analysis-server memory on a project the user had disabled. No action required.

---

14.5.8

Fixed the extension running lint analysis in the background while "Lint integration" was turned off. Disabling the integration now stops every automatic analysis trigger and background suggestion, not just the editor diagnostics. log

Fixed (Extension)

• Turning off "Lint integration" now also stops analysis triggered by saving files, changing dependencies, changing tier, changing config, and enabling a rule pack, along with the crash-coverage rule suggestion. Previously only in-editor diagnostics were suppressed. No action required.
• Turning off "Lint integration" now restarts the Dart analysis server immediately, so the plugin's background process actually exits instead of continuing to run (and hold onto several GB of memory) until the next manual reload. No action required.

Changed (Extension)

• The "Run Analysis" toolbar button is hidden while "Lint integration" is off, instead of appearing clickable and doing nothing useful. No action required.

---

14.5.7

Dependency maintenance release — no rule or extension changes. log

Maintenance

• Bumped js-yaml (extension dev dependency, via mocha) from 4.3.0 to 4.3.1, resolving GHSA-5p4m-2wfm-xmqj.

---

14.5.6

This release introduces a new rule to ensure lint suppression comments work correctly in your IDE. The require_ignore_comment_plugin_prefix rule flags ignore comments referencing saropa_lints rules that lack the required package prefix, preventing suppressions from failing silently. An automated quick fix is included to instantly apply the missing prefix. log

Added

• New rule require_ignore_comment_plugin_prefix (Essential tier, WARNING) — flags // ignore: rule_name and // ignore_for_file: rule_name comments that reference a saropa_lints rule without the required saropa_lints/ prefix, which causes the suppression to silently fail in the IDE. A quick fix inserts the prefix. No action required.
• dart run saropa_lints scan --fix-ignores — bulk-converts bare // ignore: rule_name to // ignore: saropa_lints/rule_name for all known saropa_lints rules across lib/, test/, and bin/.

Fixed

• require_ignore_comment_plugin_prefix's quick fix could insert the prefix into the wrong // ignore: comment when another ignore comment sat nearby in the file. It now targets the exact flagged comment. No action required.
• --fix-ignores skipped hyphenated rule names (e.g. avoid-null-assertion), leaving them unprefixed. It now converts them correctly. No action required.

---

14.5.5

The Analysis Optimizer now makes changes safely: it surgically updates only the patterns you're modifying while preserving your file structure, comments, and ordering, and backs up your configuration before every write for easy manual recovery. The dashboard excludes redundant recommendations when patterns are already covered and automatically rescans to keep the status current. log

Fixed (Extension)

• Analysis Optimizer could silently destroy hand-curated analysis_options.yaml structure — every Apply/Remove/Fix Syntax action rebuilt the entire exclude: block from scratch, discarding section-header comments and blank-line grouping (which aren't attached to any single pattern) and re-sorting every entry alphabetically. Writes are now surgical: only the lines for patterns actually being added or removed are touched, and every other line — comments, spacing, order — is left exactly as it was. No action required.
• Folder exclusion recommendations kept showing as "Recommended" even when already covered by a broader applied pattern (e.g. individual dependency_overrides/<package>/** entries never matched as "Applied" despite a dependency_overrides/** already excluding them). These redundant recommendations no longer appear. No action required.
• The dashboard now automatically scans on open and rescans after every Apply/Remove/Fix Syntax, instead of requiring a manual "Scan Workspace" click to see current status. No action required.

Added (Extension)

• Every Analysis Optimizer write now saves a one-step-back copy of analysis_options.yaml to analysis_options.yaml.bak first, so a change can always be manually reverted. No action required.

---

14.5.4

This release fixes the Analysis Optimizer's exclusion detection, which previously missed patterns already present in analysis_options.yaml and duplicated them on apply. The dashboard's two separate exclusion lists are now one sortable table with clearer status and impact indicators, plus a quick line preview before applying. log

Fixed (Extension)

• Analysis Optimizer could write invalid YAML that broke Dart analysis entirely — an unquoted exclude pattern starting with ** (routine for Dart globs) is YAML alias syntax, not a literal string, and caused a real Undefined alias parse error the moment the analyzer read the file. Every written pattern is now quoted, and previously-malformed unquoted entries are automatically re-quoted the next time any change is applied through the dashboard. No action required.
• Analysis Optimizer failed to detect existing exclusions — patterns with an inline # comment or a stray trailing quote (- **/*.g.dart" # ...) were never recognized as already excluded, so the dashboard kept recommending them and applying created a duplicate line. The reader now strips comments and malformed quoting before comparing, and the writer preserves each pattern's original comment on write. No action required.
• Analysis Optimizer's "Current exclusions" and "Recommended exclusions" are now one deduplicated "Exclusions" table, with an Applied/Recommended status column, sortable columns, and the chosen sort order preserved across Apply/Remove actions. No action required.
• An already-applied Analysis Optimizer exclusion that matches zero scanned Dart files (e.g. a non-Dart tool reference) now shows a dash and an explanatory reason instead of a misleading "0". No action required.

Added (Extension)

• Each Analysis Optimizer recommendation now has a "Preview" toggle showing the approximate line that would be added to analysis_options.yaml, without leaving the table. No action required.
• Analysis Optimizer now proactively warns when analysis_options.yaml already has invalid exclude syntax and offers a one-click "Fix Syntax" that re-quotes every entry, so a broken file can be repaired without needing to apply or remove a specific pattern first. No action required.

---

14.5.3

This release fixes a test-suite timeout in the health-history archival path and completes Filipino and Dutch translation coverage across the extension UI. No action required. log

Fixed

• loadHealthHistory test timeout — complexity parsing every Dart file across archived tags exceeded the 2-minute test budget. The function now accepts an optional withComplexity parameter (defaults true; test passes false).

Maintenance

• loadHealthHistory now caches each tag's computed HistoryPoint on disk (.dart_tool/saropa_lints/health_history_cache.json), keyed by the tag's resolved commit SHA. Repeat calls against unchanged tags skip re-archiving and re-scanning entirely.
• Fill fil/nl extension i18n coverage gaps for Default, Pattern, Medium, and Open analysis_options.yaml. Pattern is kept as the English loanword already used in the sibling {count} file pattern(s) string; Open analysis_options.yaml uses verb-final Dutch order to match the existing pubspec.yaml openen sibling.

---

14.5.2

This release introduces the Analysis Optimizer to help developers proactively manage their Dart analyzer's resource footprint. The extension now identifies memory-intensive files and provides an interactive dashboard for safely previewing and applying workspace exclusion patterns. By intelligently filtering out generated code and high-cost directories, users can easily maintain editor performance and swiftly resolve critical memory warnings. log

Added (Extension)

• Analysis Optimizer — new dashboard (sidebar, command palette, or memory warning toast) that scans the workspace, identifies high-cost files and folders, and recommends analyzer: exclude: patterns to reduce Dart analyzer memory usage. Applying a pattern opens a diff preview of the resulting analysis_options.yaml before writing; multi-pattern applies require confirmation. Generated code patterns (*.g.dart, *.freezed.dart, etc.) are recommended by default. No action required.
• The critical-memory toast now includes an "Optimize Analysis" button alongside "Clean Up" to surface the optimizer when the analyzer is consuming excessive memory.

---

14.5.1

This release introduces a new balanced memory mode to drastically reduce RAM consumption during incremental analysis, alongside a Full Opportunities Report designed specifically for AI-driven dependency reviews. It also refines localization workflows by eliminating false-positive translation warnings on placeholder-only templates. Developers will experience a significantly lighter background footprint on large projects and gain deeper, exportable insights into their codebase's dependency utilization. log

Added

• Full Opportunities Report — a new export (sidebar, or Saropa Lints: Export Full Opportunities Report) that consolidates every dependency and every changelog feature into one HTML, Markdown, and JSON report under reports/. Unlike the Upgrade Opportunities panel, it keeps fully-adopted packages and every changelog category, and counts each feature's usage from zero upward with the exact project file and line of every reference. Built to hand to an AI for a dependency-usage review.
• Balanced memory mode — new memory_mode: balanced setting (default) that skips type-heavy rules on unchanged files during incremental analysis, reducing CPU work on re-analysis passes. When a dependency changes, all transitive importers are automatically re-analyzed via import-graph invalidation. Set memory_mode: full in analysis_options_custom.yaml or SAROPA_MEMORY_MODE=full to restore previous behavior. No action required.

Maintenance

• Moved .vsix output from extension/ to the project root for easier access after packaging.
• Translation skip logic now recognizes placeholder-only templates ({category} ({count})) as untranslatable, eliminating 48 false-positive missing-translation reports.
• Pinned the opportunities report's symbol matcher against the implementation it replaced with a differential test, which found that the previous matcher silently never counted $-prefixed identifiers.
• Added a headless-DOM test harness (jsdom) that executes the opportunities report's inline script, so its filter, mode toggles, expand/collapse, and column sort are verified to work rather than merely to be present.
• Marked 68 rule files as type-resolution-heavy (usesTypeResolution) to support balanced memory mode filtering.

---

14.5.0

This release introduces comprehensive system health monitoring to track memory usage and safely terminate orphaned background processes. It also resolves severe memory retention issues during analysis of large codebases and refines localization workflows by preventing false-positive translation warnings. Developers will experience a significantly more stable and responsive environment with highly accurate diagnostic results during extended coding sessions. log

Added

• System health monitor in the VS Code extension: polls Dart/Flutter process memory and orphaned daemon count every 60 seconds (Windows). Status bar shows a warning or critical suffix when memory exceeds configurable thresholds or orphaned daemons accumulate. One-click "Kill Orphaned Flutter Daemons" command re-queries live processes before killing, avoiding stale-PID risks. All thresholds configurable via extension settings under "System Health".
• Process Health panel (Command Palette → "Process Health"): live table of all Dart/Flutter processes with PID, parent, RSS, type classification (process/daemon/orphan), and per-process kill buttons for orphaned daemons.

Fixed

• Register 25+ internal caches for eviction under memory pressure — previously only 10 of ~70 were managed, causing unbounded memory growth on large projects (7.8 GB observed on a 3,900-file codebase). No action required.
• Fix memory estimator to measure actual per-file cache sizes instead of flat approximations that understated real usage by ~25×. No action required.
• Cap the per-file passed-rules cache with LRU eviction (default 500 files) — the single largest memory consumer at O(files × rules), previously unbounded. No action required.
• Cap the per-file diff cache with LRU eviction (default 250 files) — retained full source text of every analyzed file (~19.5 MB on a 3,900-file project), now bounded. No action required.
• Release per-file tracking maps after the analysis summary is reported — previously retained indefinitely, wasting memory for the rest of the session. No action required.
• Fix VS Code integrated terminal color detection on Windows — ANSI escape sequences now render correctly when TERM_PROGRAM is set. No action required.

Maintenance

• Add infrastructure bug report for orphaned flutter daemon processes accumulating on Windows and exhausting system RAM. Includes hardened cleanup scripts with PID-reuse detection, a scheduled task to break the OOM feedback loop, and a Win32 Job Object permanent fix concept.
• Add PID, RSS, Daemon to MT do-not-translate list and expand skip logic for emoji+placeholder patterns (⚠ {size}, 🔴 {size}), resolving 71 false-positive missing-translation entries across 24 locales. No action required.

---

14.4.3

Resolves a runtime error in the lint diagnostic reporter that could prevent ignore-comments and deduplication checks from functioning correctly. This release also hardens internal code quality with broad static analysis improvements and introduces new automated CI gates to prevent future regressions. log

Fixed

• Fix undefined ruleContext reference in SaropaLintRule.registerNodeProcessors — the diagnostic reporter was receiving an unresolved identifier instead of the method's RuleContext parameter, which could cause ignore-comment and dedup checks to fail at runtime. No action required.

Maintenance

• Resolve unnecessary_string_interpolations, unnecessary_string_escapes, and prefer_adjacent_string_concatenation lint issues across lib/ to future-proof against pana baseline upgrades to package:lints/recommended.yaml. No action required.
• Resolve 209 dart analyzer lint issues across lib/ and test/: nullable final variables, string interpolation style, dangling library doc comments, unnecessary this/late, missing @override, prefer_contains, use_super_parameters, prefer_collection_literals, and parameter naming alignment with base class signatures.
• Remove dead field _isProjectRootInitialized from SaropaLintRule.
• Add scripts/check_dart_fix.py — CI gate that fails if fixable dart issues exist; hardened with multiple regex patterns and error handling for missing dart or timeout.
• Integrate dart fix --dry-run / --apply into the publish pipeline as an auto-fix step before blocking checks.
• Add // ignore: suppressions for 5 unfixable recommended.yaml issues (implementation_imports, library_private_types_in_public_api, prefer_interpolation_to_compose_strings) with verified rationale comments.
• Add scripts/check_recommended_yaml.py — CI gate that temporarily enables recommended.yaml analysis and asserts zero unsuppressed issues; preserves original file bytes on restore, handles YAML document markers and missing dart.
• Add dart fix and recommended.yaml checks to pre-commit hook — regressions are now caught before push; dart availability is checked by each Python script (exit 2 = skip), not the shell.

---

14.4.2

Static analysis fixes. log

Fixed

• Fix 41 static analysis issues flagged by pub.dev pana scoring (unnecessary null checks, unused imports, missing curly braces, dead code, redundant ignores, invalid overrides)

---

14.4.1

Ignore: Published build error - mixed code/versions. Ignore.

---

14.4.0

Introduces a new lint rule to catch invalid date initializations that would otherwise silently roll over into incorrect dates. Developers are now guided toward strict parsing methods to make date handling safer across Dart and Flutter projects. log

Added

• avoid_datetime_constructor — flags DateTime() and DateTime.utc() constructors, which silently roll over out-of-range values (e.g. month 13 becomes January of the next year). All-literal in-range calls are allowed. Quick fix available: replace with DateTime.tryParse(). No action required.
• avoid_datetime_constructor_unvalidated — flags DateTime() calls whose result is consumed directly (returned, passed as argument, used in field initializer) without being assigned to a local variable where components can be validated. No action required.

---

14.3.13

Fix false positive in avoid_bluetooth_scan_without_timeout — the rule no longer fires on non-Bluetooth scan() calls. log

Fixed

• avoid_bluetooth_scan_without_timeout no longer flags scan().listen() on non-Bluetooth receivers (e.g. dedup scanners, port scanners). No action required.
• require_bluetooth_state_check now recognizes additional Bluetooth package types (flutter_reactive_ble, bluetooth_low_energy, quick_blue, universal_ble). No action required.
• avoid_bluetooth_scan_without_timeout skips files without scan-related strings via requiredPatterns pre-filter, reducing unnecessary AST traversal. No action required.

---

14.3.12

Re-release of v14.3.10 with a build fix — no rule or extension changes. log

Maintenance

• Fix test compilation error that blocked the v14.3.10 publish pipeline. No action required.
• Extract shared parseMethodBody test helper and add CI guard against childEntities usage on class-like declarations. No action required.

---

14.3.11

Skipped: Internal build only.

---

14.3.10

Resolves false positives across matrix scaling operations and resource disposal lints. Uniform scaling factors in matrix transformations are no longer incorrectly flagged as duplicate arguments, and cleanup rules now properly recognize cascade syntax when disposing of controllers, streams, and timers. log

Fixed

• Fix: no_equal_arguments false positive on Matrix4 uniform scaling — scaleByDouble(s, s, 1, 1), scale(s, s, 1), and diagonal3Values(s, s, 1) no longer flag the repeated factor as a copy-paste error. The scale exemption is receiver-type-guarded to Matrix4 only, so myWidget.scale(x, x) still fires.
• Fix: disposal rules false positive on cascade syntax — all disposal/cleanup rules (require_text_editing_controller_dispose, require_page_controller_dispose, stream/timer cancel rules, etc.) now recognize _field..dispose() and _field..close() cascade expressions as valid cleanup. Previously only _field.dispose() and _field?.dispose() were matched.

Maintenance

• Fix cascade cleanup test helper to use ClassDeclaration.body.members instead of childEntities, which stopped exposing MethodDeclaration in analyzer 12.1.0.

---

14.3.9

Two new comprehensive rules help monitor native bridge performance by requiring the @MethodChannelInstrumented annotation on channel classes and ensuring those calls are wrapped in timing helpers like noteIfSlow. log

Added

• New rule: require_method_channel_instrumented — flags classes that call MethodChannel.invokeMethod / invokeListMethod / invokeMapMethod without a @MethodChannelInstrumented annotation, one diagnostic per class. Quick fix inserts the annotation. Comprehensive tier.
• New rule: prefer_method_channel_note_if_slow — flags bare invoke-method calls inside @MethodChannelInstrumented classes that are not wrapped in noteIfSlow or an equivalent timing helper. Comprehensive tier.

Maintenance

• Fix: rule packs UI in self-package — the Config Dashboard's "Enable all" and individual pack toggles produced misleading toasts ("already enabled" / "could not write") when the workspace is the saropa_lints package itself. The extension now detects the self-package via name: saropa_lints in pubspec, treats the implicit plugin load as configured, and creates a plugins: saropa_lints: block when no anchor exists for rule_packs writes.
• CI: full clone for test job — the health_history_test needs git tags; shallow CI clones lacked them. Changed to fetch-depth: 0 (full clone) so tags and history are always available.
• Security: fix 3 Dependabot alerts — upgraded shell-quote 1.8.4 → 1.10.0 (quadratic DoS in parse()), replaced abandoned npm-run-all with maintained npm-run-all2@8, and overrode brace-expansion to patched versions (exponential DoS). All dev-only dependencies.
• Dependabot: grouped weekly schedule — added .github/dependabot.yml to batch all extension npm security updates into a single weekly PR (Mondays) instead of one PR per alert.
• i18n engine: NLLB → Qwen — the extension's machine-translation pipeline now uses Qwen 3 via local Ollama as the primary engine, with Google Translate as the per-string fallback. NLLB is deprecated; existing NLLB-provenance translations are treated as low-quality and re-translated on the next --mode upgrade run. No user action required.
• i18n: LLM control-token rejection — the translation cache validator now rejects cached strings containing leaked LLM control tokens (/no_think, <|endoftext|>, [INST], etc.). Contaminated entries auto-heal on the next translation run. GPU detection is deferred to first use so importing the engine no longer runs nvidia-smi.

14.3.8

Fixes an issue where the analysis server repeatedly restarted the plugin isolate, causing IDE diagnostic results to clear continuously. Automatically excludes common non-Dart output directories during initialization to prevent file-watcher feedback loops. Adds restart-rate telemetry, log rotation, and a configurable log_level setting to control plugin log verbosity. log

Fixed

• Plugin isolate restart storm — the analysis server respawned the plugin isolate hundreds of times per day (13,660 over 91 days on the contacts project), clearing all diagnostics from the Problems tab each time. Two causes addressed: (1) Plugin.start() now skips config loading when the working directory is not a Dart project (e.g. the VS Code install directory), eliminating the 0-rules phase and noisy log entries; (2) PluginLogger.setProjectRoot() now validates that the root contains pubspec.yaml before writing log files, preventing log writes into non-project directories that could trigger file-watcher restarts.
• Init command: non-Dart directories now excluded from analyzer — dart run saropa_lints:init and the headless config writer now ensure common non-Dart directories (reports/**, docs/**, bugs/**, plans/**, doc/**, output/**, tmp/**) are in the analyzer > exclude list. Without this, plugin log writes to reports/.saropa_lints/ could trigger the analysis server's file watcher and restart the plugin isolate in a feedback loop.
• Plugin logger: restart-rate telemetry — after each isolate spawn, PluginLogger counts recent "session started" entries in the log file. When the rate exceeds 10 restarts in 10 minutes, a WARNING line is emitted with remediation advice. The log file itself is the durable counter since statics reset per isolate.
• Init command: flow-style YAML guard — ensureNonDartExcludes now detects flow-style exclude: [...] under the analyzer: section and leaves it unchanged instead of inserting a duplicate exclude: key. Trailing comments after exclude: are also handled correctly.
• Plugin logger: log rotation — plugin.log is now capped at 512 KB; oldest content is discarded at each isolate start, bounding the cost of the restart-rate telemetry read and preventing unbounded disk growth. No action required.

Added

• Plugin logger: configurable log level — new log_level: key under plugins > saropa_lints in analysis_options.yaml controls which messages are written to plugin.log. Valid values: off, error, warning, info (default), debug. Messages below the configured level are still sent to the analysis server's developer log but skip the user-visible file. The init command writes log_level: info by default.
• Plugin logger: convenience API — PluginLogger.debug(), .warning(), and .error() replace the level: named parameter pattern, making log call sites more concise. Unrecognized log_level values now emit a warning instead of silently falling back to info. Tab-indented configs are now parsed correctly.

---

14.3.7

Updates the Dio linting behavior to favor dependency injection and factory patterns over static singletons. The updated rule flags top-level and static Dio declarations while permitting instantiation inside methods, constructors, and callbacks, resolving an architectural contradiction with anti-singleton guidelines. log

Changed

• Breaking: Renamed require_dio_singleton to require_dio_factory — the rule now flags Dio() in static fields and top-level variables (the singleton anti-pattern) instead of recommending them. Dio() inside methods, constructors, closures, and DI callbacks is allowed. Resolves the architectural contradiction with avoid_singleton_pattern (#274). No action required if already using factory/DI patterns.
• require_dio_factory config alias: Projects using require_dio_singleton in analysis_options.yaml continue working via configAliases — no config migration required on upgrade.

Added

• Hardened require_dio_factory detection: Added coverage for late static final Dio fields, static getters, nested closures, and mixin method bodies. No action required.

Maintenance

• Closed Dependabot PR #271 bug (js-yaml 4.1.1 → 4.3.0): lock file already resolves to 4.3.0 via mocha; archived as fixed.
• Publish audit now detects dangling bugs/*.md references in active documents (skips frozen plans/history/).

---

14.3.6

Removes the avoid_debug_print rule, which contradicted the existing prefer_debug_print and left no valid console output path. Also fixes false positives in avoid_redundant_null_check and avoid_redundant_await when types are nullable or resolve across package boundaries. A new --debug-rule flag on the scan CLI traces type resolution for any named rule, making it easier to diagnose false positives. log

Removed

• avoid_debug_print rule deleted. The rule contradicted prefer_debug_print — one said "use debugPrint," the other said "don't" — leaving no valid console output function for projects without a custom logging wrapper. prefer_debug_print remains and covers the print() → debugPrint() upgrade path. No action required unless your config explicitly enabled avoid_debug_print; if so, remove the entry.
• CommentOutDebugPrintFix quick fix deleted (was the only fix for the removed rule). No action required.

Added

• --debug-rule <name> flag for the scan CLI. Emits per-node type-resolution trace output (staticType, staticInvokeType, returnType) for the named rule during a scan. Use with --resolve for full type information. Designed for diagnosing false positives caused by type-resolution divergence in the analyzer plugin context. No action required.

Fixed

• avoid_redundant_null_check no longer fires on variables, parameters, fields, or getters declared with a nullable type (Type?). The rule cross-checks the element's declared type against the resolved staticType and guards against InvalidType from failed type resolution, preventing false positives in cross-package contexts.
• avoid_redundant_await no longer fires on await of static methods returning Future<T>. The rule now guards against InvalidType (unresolvable types) and falls back to checking the invoked method signature's return type via staticInvokeType when staticType fails to resolve for cross-file static invocations.

---

Historical Changelog Archive

Looking for older changes? See CHANGELOG_ARCHIVE.md for older versions.