Repository navigation
fix(tray): close the 16 findings of the macOS tray UX + settings-parity audit - #1055
Merged
Merged
Conversation
…rity audit Menu-bar icon now badges server severity and is labelled for VoiceOver; per-server actions report failure instead of closing silently; a "Needs Attention" row navigates and its remediation lives under its own verb. Agent Tokens and a new global Tools search reach the sidebar, the Servers submenu groups by state, and the settings catalogue regains the three web-only fields behind a full key-coverage parity gate.
Deploying mcpproxy-docs with
|
| Latest commit: |
c173342
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://d2fd355c.mcpproxy-docs.pages.dev |
| Branch Preview URL: | https://fix-tray-ux-audit.mcpproxy-docs.pages.dev |
Cross-model review round 1: escape query values (urlQueryAllowed lets &/=/+ through), carry the sub-call and session filters into the activity export, count only the badged severity in the status-item label, treat a newline-only optional field as unset, and widen the settings parity gate to control/restart/options with comment stripping and duplicate detection.
Cross-model review round 2: server names are only validated against ':',
so 'my/server' would split the /servers/{id}/... path the menu's enable,
disable, restart and sign-in actions all post to.
Cross-model review round 3: publish the pending session on AppState so a window created by the click picks it up on appear (a delayed notification lands before ActivityView subscribes), and make the parity gate refuse a non-string-literal field key instead of silently skipping it.
|
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
Contributor
📦 Build ArtifactsWorkflow Run: View Run Available Artifacts
How to DownloadOption 1: GitHub Web UI (easiest)
Option 2: GitHub CLI gh run download 32848108497 --repo smart-mcp-proxy/mcpproxy-go
|
github-actions Bot
pushed a commit
that referenced
this pull request
Aug 25, 2026
…ve catalog (#1056) PR #1050 marked the field restart-required in the Web UI one minute before PR #1055 landed the widened settings-parity gate; neither branch saw the other, and native-tests.yml is path-filtered to native/**, so main went red on a job that had not run since 08-22. One-line catalog sync; parity now reports 58 settings consistent.
Dumbris
added a commit
that referenced
this pull request
Aug 26, 2026
The document read as an open backlog, but #1055 ("fix(tray): close the 16 findings of the macOS tray UX + settings-parity audit", merged 2026-08-25) fixed all 16, with #1056 as a catalogue follow-up. The header's "no version skew, so every finding below is reproducible from source" is no longer true against main. - Header scopes that claim to the time of the walk and carries a status banner. - New §6 Resolution records the two fixes whose obvious implementation is wrong: F1's severity dot is an attributed-title glyph, not a composite image (the status image stays isTemplate and a template image renders monochrome), and F6 added a parity gate rather than just the three missing keys. - Verified on main rather than taken on trust: Menu/TrayIcon.swift is deleted, TokensView is reachable from Views/MainWindow.swift, MCPProxyApp.swift sets isTemplate + accessibilityDescription + toolTip + attributedTitle glyph, and SettingsCatalog.swift carries deep_scan / instructions / code_execution_max_parallel. Note for anyone tracing this later: #1053's body claims to fix these 16 tray findings, but #1053 touches no Swift file — it is the Web UI cluster its own title names. #1055 is the tray PR. The caveat is stated rather than hidden: this pass could not re-walk the live tray, because macOS Accessibility was revoked on the reviewing machine (check_accessibility -> trusted:false), so the resolution is read from the #1055 diff, not from a second walk.
Dumbris
added a commit
that referenced
this pull request
Aug 26, 2026
The document read as an open P0-P3 backlog, but seven PRs merged on 2026-08-25 (#1044, #1048, #1049, #1051, #1052, #1053, #1054) closed it. Anyone opening this file against current main was being handed 36 stale defects. Added a status banner and a Resolution section that separates three things honestly: - Re-checked live on v0.61.0 against a running isolated core with real /mcp traffic: F1, F4, F5, F7, F8, F12, F13, F20, F24, F26, F33 confirmed fixed, each with the observed evidence rather than a PR reference. - Still open: F6 is half fixed. Focus enters the Add Server dialog and submit is in a sticky footer, but Escape still does not close it - AddServerModal.vue has no key handler and JsonViewer.vue is the only component under components/ that handles Escape at all. F28's "key called optional" half is fixed; its three-surfaces state is not. - Not re-checked: named explicitly rather than implied, so the next reader knows which closures rest on a PR body and which on an observation. Five defects found on main while re-checking are recorded separately, since they are not regressions of anything in the audit. The first is security-relevant: quarantining a server through the config file leaves its tools in the search index, so retrieve_tools still hands the agent their names and descriptions - which is exactly what quarantine exists to prevent - before the call is refused. Runtime.QuarantineServer purges the index; the reload path detects the same transition (quarantined_changed: true) and does not. Also corrects the record on #1053: its body names F1-F16, which is the tray audit's numbering mis-pasted. #1055 is the tray PR; #1053 touches no Swift file.
Dumbris
added a commit
that referenced
this pull request
Aug 26, 2026
The document read as an open P0-P3 backlog, but eight PRs merged on 2026-08-25 (#1044, #1048, #1049, #1050, #1051, #1052, #1053, #1054) closed it. Anyone opening this file against current main was being handed 36 stale defects. Added a status banner and a Resolution section that separates four things: - Re-checked live on v0.61.0 against a running isolated core with real /mcp traffic: F1, F4, F5, F6, F7, F8, F12, F13, F20, F24, F26, F33 confirmed fixed, each with the observed evidence rather than a PR reference. - Not re-checked: named explicitly rather than implied, so the next reader knows which closures rest on a PR body and which on an observation. F28 is called out as partial - its "key called optional" half is fixed, its three-surfaces-at-once state is not. - Corrections to the audit itself: F23 mis-diagnosed a per-request structural estimate as a stale aggregation, and F31's "Manual badge has no tooltip" half was wrong even at audit time (spec-088 trust-mode badge, already titled). - Five defects found on main while re-checking, recorded separately since they are not regressions of anything in the audit. The first is security-relevant: quarantining a server through the config file leaves its tools in the search index, so retrieve_tools still hands the agent their names and descriptions - which is exactly what quarantine exists to prevent - before the call is refused. Runtime.QuarantineServer purges the index; the reload path detects the same transition (quarantined_changed: true) and does not. F6 carries a methodology note. Re-checking it produced a false negative: Escape driven through the browser-automation layer never reaches the page's document keydown listener, so the dialog looked stuck open. Dispatched in-page it closes at once, and #1050's useModalA11y is wired into all five <dialog :open> modals. The sweep assertion this document proposes must dispatch in-page, or it tests the automation layer instead of the app. Also corrects the record on #1053: its body names F1-F16, which is the tray audit's numbering mis-pasted. #1055 is the tray PR; #1053 touches no Swift file.
Dumbris
added a commit
that referenced
this pull request
Aug 26, 2026
Replaces the "could not re-walk" caveat with the walk itself. macOS Accessibility was granted, so mcpproxy-ui-test works now; the walk reproduces this audit almost verbatim, because the installed tray is still v0.60.0 with "Update 0.61.0 — ready to restart?" sitting in the menu. Reproduced live: F2 (empty status-bar title, no description, no tooltip), F5 (no Agent Tokens entry), F7 (ElevenLabs "Stop" vs cloudflare-graphql "Disable"; and memory showing status Disabled above action Start), F8 (all three quarantined servers offer only Disable/Stop, Restart, View Logs), F11 (research and deploy still offered at 0 tools), F12 (streamable-http beside http and sse), F15 (29 flat entries), F16 (no tool search), and the pre-#1055 menu labels. One drift worth noting: the Clients block now reads "No clients in the last 24h" rather than listing an idle client - the empty state H5 exists to avoid. The consequence for the resolution section: #1055's fixes are real in the diff but remain unverified against a running tray. That needs the pending 0.61.0 restart or the dev bundle-swap, neither of which this pass did - restarting the tray kills the core it manages.
Dumbris
added a commit
that referenced
this pull request
Aug 26, 2026
* docs(qa): Web UI UX audit — ranked findings (ux-audit epic) Heuristic + live-instance audit of every routed Web UI view in light/dark, first-run and populated states, at 1440/820/390px. 36 findings ranked P0-P3 with view, evidence, heuristic violated, suggested fix and effort. Audited against standard heuristics plus the house activity-UI rules (grouping, failure-only status, intent reason, histogram/log parity). * docs(qa): record what the Web UI audit's backlog actually resolved to The document read as an open P0-P3 backlog, but eight PRs merged on 2026-08-25 (#1044, #1048, #1049, #1050, #1051, #1052, #1053, #1054) closed it. Anyone opening this file against current main was being handed 36 stale defects. Added a status banner and a Resolution section that separates four things: - Re-checked live on v0.61.0 against a running isolated core with real /mcp traffic: F1, F4, F5, F6, F7, F8, F12, F13, F20, F24, F26, F33 confirmed fixed, each with the observed evidence rather than a PR reference. - Not re-checked: named explicitly rather than implied, so the next reader knows which closures rest on a PR body and which on an observation. F28 is called out as partial - its "key called optional" half is fixed, its three-surfaces-at-once state is not. - Corrections to the audit itself: F23 mis-diagnosed a per-request structural estimate as a stale aggregation, and F31's "Manual badge has no tooltip" half was wrong even at audit time (spec-088 trust-mode badge, already titled). - Five defects found on main while re-checking, recorded separately since they are not regressions of anything in the audit. The first is security-relevant: quarantining a server through the config file leaves its tools in the search index, so retrieve_tools still hands the agent their names and descriptions - which is exactly what quarantine exists to prevent - before the call is refused. Runtime.QuarantineServer purges the index; the reload path detects the same transition (quarantined_changed: true) and does not. F6 carries a methodology note. Re-checking it produced a false negative: Escape driven through the browser-automation layer never reaches the page's document keydown listener, so the dialog looked stuck open. Dispatched in-page it closes at once, and #1050's useModalA11y is wired into all five <dialog :open> modals. The sweep assertion this document proposes must dispatch in-page, or it tests the automation layer instead of the app. Also corrects the record on #1053: its body names F1-F16, which is the tray audit's numbering mis-pasted. #1055 is the tray PR; #1053 touches no Swift file.
Dumbris
added a commit
that referenced
this pull request
Aug 27, 2026
* docs(qa): macOS tray UX + settings-parity audit Read-only sweep of the running v0.60.0 tray (accessibility-tree menu walk) plus a static comparison of the tray's native surfaces and settings catalogue against the Web UI. Parity matrix (feature surfaces, settings fields, per-server actions) and 16 ranked findings: dead menu-bar health badge, unlabelled status item, silent action failures, unreachable Agent Tokens view, and three settings fields that drifted out of the tray catalogue. * docs(qa): mark the tray audit resolved, and say what was not re-verified The document read as an open backlog, but #1055 ("fix(tray): close the 16 findings of the macOS tray UX + settings-parity audit", merged 2026-08-25) fixed all 16, with #1056 as a catalogue follow-up. The header's "no version skew, so every finding below is reproducible from source" is no longer true against main. - Header scopes that claim to the time of the walk and carries a status banner. - New §6 Resolution records the two fixes whose obvious implementation is wrong: F1's severity dot is an attributed-title glyph, not a composite image (the status image stays isTemplate and a template image renders monochrome), and F6 added a parity gate rather than just the three missing keys. - Verified on main rather than taken on trust: Menu/TrayIcon.swift is deleted, TokensView is reachable from Views/MainWindow.swift, MCPProxyApp.swift sets isTemplate + accessibilityDescription + toolTip + attributedTitle glyph, and SettingsCatalog.swift carries deep_scan / instructions / code_execution_max_parallel. Note for anyone tracing this later: #1053's body claims to fix these 16 tray findings, but #1053 touches no Swift file — it is the Web UI cluster its own title names. #1055 is the tray PR. The caveat is stated rather than hidden: this pass could not re-walk the live tray, because macOS Accessibility was revoked on the reviewing machine (check_accessibility -> trusted:false), so the resolution is read from the #1055 diff, not from a second walk. * docs(qa): correct two §1 claims that were wrong at the time of the walk Verified against v0.60.0 rather than taken on trust: - The tray Settings tab is named "Raw", not "Raw JSON" (native/macos/MCPProxy/MCPProxy/Views/SettingsView.swift:38 at v0.60.0). The §1.2 inventory, the §2 parity matrix and F6's body all said "Raw JSON". - The Web UI had no /usage route at v0.60.0 - the router's path list runs /, /servers, /repositories, /search, /settings, /secrets, /sessions, /tools, /activity, /security, /tokens with no usage or overview entry. Usage was a Dashboard tab; /usage became a route later, in #1044. The parity matrix's "Usage report | ⚠ savings % on Dashboard | ✅ /usage | inconsistent" overstated the Web UI side of that comparison. Also noted in §6 that three §1.1 menu labels have changed since the walk as part of the F9 fix: Open MCPProxy Window, Open Web UI in Browser, Launch at Login. * docs(qa): re-walk the live tray and record that the findings still hold Replaces the "could not re-walk" caveat with the walk itself. macOS Accessibility was granted, so mcpproxy-ui-test works now; the walk reproduces this audit almost verbatim, because the installed tray is still v0.60.0 with "Update 0.61.0 — ready to restart?" sitting in the menu. Reproduced live: F2 (empty status-bar title, no description, no tooltip), F5 (no Agent Tokens entry), F7 (ElevenLabs "Stop" vs cloudflare-graphql "Disable"; and memory showing status Disabled above action Start), F8 (all three quarantined servers offer only Disable/Stop, Restart, View Logs), F11 (research and deploy still offered at 0 tools), F12 (streamable-http beside http and sse), F15 (29 flat entries), F16 (no tool search), and the pre-#1055 menu labels. One drift worth noting: the Clients block now reads "No clients in the last 24h" rather than listing an idle client - the empty state H5 exists to avoid. The consequence for the resolution section: #1055's fixes are real in the diff but remain unverified against a running tray. That needs the pending 0.61.0 restart or the dev bundle-swap, neither of which this pass did - restarting the tray kills the core it manages.
3 tasks done
Dumbris
added a commit
that referenced
this pull request
Aug 28, 2026
#1075) * fix(tray): stop the permanent red badge, and shrink it to a corner dot The v0.61.0 tray badge (#1055) sat red indefinitely on an install whose only error-severity diagnostics belonged to quarantined servers, and it was drawn as a full-size glyph beside the icon rather than a badge on it. Tray badge — quarantined servers no longer tint it worstDiagnosticSeverity and diagnosticCount excluded OAuth login-required servers but not quarantined ones. mcpproxy still attempts a connection to a quarantined server so the scanner can export its tool definitions, and the failed attempt leaves an error-severity diagnostic behind — while the same payload reports health.level "healthy" / admin_state "quarantined". The menu header drew a calm yellow dot from serversNeedingAttention under a red menu-bar dot from worstDiagnosticSeverity, and the user could not clear it without approving or disabling the server. Both properties now share one ServerStatus.isBadgeExempt predicate so they cannot drift apart, and any future intentional non-connected state has one place to be added. Tray badge — drawn as a corner dot, not a glyph beside the icon The severity badge was a full-size "●" plus a leading space in the button's attributed title, which widened the status item by about a character and read as a second icon. It is now a 6pt dot in the icon's bottom-right corner, as a subview: the status-item image must stay isTemplate to track the light/dark menu bar and to invert while the menu is open, and template rendering forces every pixel monochrome, so a coloured dot composited into the image comes back black. The view is hit-test transparent and ignored by accessibility, since the button already publishes the whole state as its label. ⏹ (core stopped) and ⚠ (core error) keep their full-size glyphs: those mean "nothing is working", which is worth the width and would be lost if collapsed into the same dot. Diagnostics — two of mcpproxy's own messages no longer say "file a bug" `command "npx" has no args` (emitted by our own pre-spawn validation in connection_stdio.go) and the legacy-SSE `4xx for initialize POST` both fell through to MCPX_UNKNOWN_UNCLASSIFIED, whose catalog entry offers a "Report a bug" button. They now classify as MCPX_CONFIG_INVALID_COMMAND and MCPX_HTTP_LEGACY_SSE, with catalog entries and docs pages. The legacy-SSE rule is matched before the generic HTTP status-text fallback, which would otherwise claim it as a bare 403/404 and send the user hunting for a credential problem that does not exist. Logging — one ListTools failure was three ERROR lines core.Client, managed.Client and Manager.discoverTools each logged the same failed list operation at ERROR. On an install with several stdio servers the periodic sweep hit this roughly once a minute per server, indefinitely. The two inner layers drop to Debug; the manager keeps the line at Warn, since it deliberately skips markSwept so the next sweep retries — a failure the code already plans to retry is not an error. Tests - Swift: quarantine/OAuth badge exemption from live /api/v1/servers payload shapes, including that a genuinely broken server still tints red and that the spoken count agrees with the badge. - Swift: corner-dot geometry and colour asserted by rendering the view offscreen and reading pixels back — the status item cannot be screenshotted without a Screen Recording grant, and "it looked right once" is not a regression test. - Go: both new codes classify from the verbatim v0.61.0 error strings, ordinary HTTP statuses are unaffected, and both codes are registered. - Go: one ListTools failure is reported by exactly one layer, not at ERROR, and is still reported at all. * fix(tray): anchor the badge dot to the icon, not the button Cross-model review (opencode, gpt-5.6-sol) caught a real defect in the corner-dot badge: it was a 6x6 subview positioned from `button.bounds` at update time and pinned with `[.minXMargin, .maxYMargin]`. That anchors to the BUTTON's bottom-right, but the dot belongs to the CENTRED 18pt icon, and it broke in two independent ways. * Rate mismatch. When the status button shrinks by N, a right-pinned subview moves left by N while the centred icon's right edge moves left by only N/2 — the badge slides off the glyph it is badging. * Stale bounds. NSStatusItem is variableLength and resizes asynchronously, so the `button.bounds` read immediately after clearing `attributedTitle` (which updateStatusIcon does, in the same pass) is still the old, wider value. The dot is then laid out against an icon centre that no longer exists. The overlay now fills the button, autoresizes with `[.width, .height]`, and computes the dot inside `draw(_:)` from its own live bounds. Any resize simply repaints in the right place, which removes both failure modes rather than patching either. `hitTest` already returned nil, which is what keeps the now-full-size overlay from swallowing every click. Note `needsDisplayOnBoundsChange` is a CALayer property and does not exist on NSView — the review suggested it and it does not compile. `setFrameSize` is overridden instead. Tests The drawing tests now RENDER the view and scan the bitmap for the pixels it actually painted, converting device pixels to points, rather than sampling one computed point. The earlier version guessed the bitmap's y-flip, read a transparent pixel, and would have reported "the view drew nothing" as a colour failure. Scanning asserts position, colour and restraint together and survives a geometry retune. Added: - the dot tracks the icon across button widths (the regression above) - a resize re-renders it in its new place - only the corner dot is painted, never a wash over the whole icon * fix(tray): the status button is FLIPPED — pin it, test it, document it Multi-agent verification found what both I and the cross-model review missed, by compiling against real AppKit rather than reasoning about it: NSView().isFlipped = false NSButton().isFlipped = true NSStatusBarButton.isFlipped = true The first commit in this PR (9c740c0) therefore shipped the badge in the icon's TOP-right corner, not the bottom-right its comment and commit message both claimed. `y = 2` in a flipped button is 2pt from the TOP, and `.maxYMargin` pins to the TOP. Rendered inside a real 36x22 status button the dot landed at bitmap rows 4-15 of 44 (top-first). The second commit (5e773a9) already corrected it — but incidentally, because TrayBadgeDotView is a plain NSView and computes the dot in its own unflipped space. Nothing recorded that the design depends on that, and no test could tell the two apart: every badge test rendered the view standalone, where the flip never enters the picture. * `isFlipped` is now overridden to `false` explicitly. It is load-bearing, not incidental — overriding it to true silently moves the badge back to the top-right. * TrayBadgeDotView's and badgeDotFrame's comments described the OLD bug wrongly (they said the mask pinned bottom-right). Corrected, with the flipped-coordinate trap written down as the reason the design is shaped the way it is. * New TrayBadgeInStatusButtonTests renders the overlay inside a REAL NSStatusBarButton and asserts the dot is in the visual lower-right. Mutation-tested: flipping the overlay fails it with "badge is in the TOP half — the flipped-coordinate bug is back (rows 4...15 of 44)", matching the shipped bug's measured position exactly. Also from the sweep: * The legacy-SSE string is mcp-go's exported `transport.ErrLegacySSEServer`, NOT one of ours as the classifier comment, the test file and the PR body all claimed. Corrected, `errors.Is` added as the primary check (the substring fallback stays, since the upstream layer stringifies the error and breaks the errors.Is chain), and TestLegacySSESentinelStillMatches pins the vendored wording — otherwise a routine mcp-go bump silently regresses MCPX_HTTP_LEGACY_SSE to MCPX_HTTP_404 with the suite green. * `serversWithDiagnostic` was left on the narrower OAuth-only predicate when isBadgeExempt was introduced, breaking the "these filter identically" invariant at birth. Nothing consumes it today, which is precisely why the drift would have surfaced late. Aligned, and pinned by a test. * `isQuarantineReview`'s comment claimed `quarantined` and `admin_state` were two independent signals. They are not — health/calculator.go derives the second from the first. The check is kept as belt-and-braces; the claim is corrected. * Added the composition case nothing covered: servers are quarantined on add, so a newly added npx-with-no-args server is quarantined AND broken. It asks for review rather than raising a red badge — deliberate, now pinned, along with the case that it DOES alarm once released. * test(tray): skip the status-button render test when there is no window server TrayBadgeInStatusButtonTests creates a real NSStatusBar item, which is the whole point — the flipped-coordinate bug is invisible to a standalone render. But `swift test` runs on a macos-latest runner whose window-server state is not guaranteed, and there `item.button` is nil. XCTUnwrap turned that into a FAILURE, so a green local run could have gone red in CI for a reason the test cannot assert there. Throws XCTSkip instead. The assertions are about AppKit geometry inside a real button; with no button there is nothing to assert, and that is a skip, not a defect.
Dumbris
added a commit
that referenced
this pull request
Aug 29, 2026
…inish the ux-audit sweep (#1085) * chore(roadmap): truth-sync ux-audit and upgrade-nudge Two epics claimed a state the repo contradicts. upgrade-nudge was `done` with all four tasks done, but Spec 079 FR-002 — the human-readable "N releases / M weeks behind" delta required on status, doctor, the startup log, the Web UI and both trays — was never built. The four shipped tasks are US-slices and the FR belonged to none of them; spec 079 has only spec.md, so no checkbox surface could catch the gap. It survived only as TODO(spec-079/FR-002) comments in internal/updatecheck/checker.go and cmd/mcpproxy/status_cmd.go, which is how an outside contributor found it (#1081). Epic back to in_progress with an explicit upgrade-nudge-delta task. ux-audit was `todo` with both sweeps todo, but both shipped in August (#1046 Web UI, 36 findings; #1043 macOS tray, 16 findings) along with ten PRs closing every finding and the five defects the re-check pass raised (#1061/#1064/#1065, all closed). Recorded the sweeps and fix waves as done and added the two items that really are open: folding the audit's F6 modal Escape/focus and F1 cross-view total assertions into e2e/web-ui-sweep, and verifying the tray fixes on a running tray (the 2026-08-26 re-walk found the installed tray still on v0.60.0, so #1055 remains unobserved). Also cleared the two --check-github errors, neither introduced here: - tpa-db and mcp-2026-upgrade each linked a docs(specs) PR in `pr:`. That field is implementation evidence, so a spec merge read as "epic done". Both entries' own notes already said implementation had not started; moved the refs into the notes and left the statuses honest at todo. - analytics-default-landing (#1044) and schema-deferred (#1063, tasks.md 89/89) were genuinely finished and are now done. * feat(079): "N releases / M weeks behind" upgrade delta (FR-002) Closes the last outstanding slice of Spec 079. FR-002 requires the current version, the latest version AND a human-readable delta on `mcpproxy status`, `doctor`, the startup log, the Web UI and both trays; what shipped was latest-version-only, and the deferral survived as TODO(spec-079/FR-002) comments that an outside contributor found (#1081). The blocker was data, not rendering: the checker fetched only /releases/latest, so it had the offered release's publish date but not the running one's, and no tag sequence to count. internal/updatecheck/delta.go computes the delta as a pure, network-free, clock-free function, so every spec rule is a table row. Fetching is a best-effort enrichment hung off the existing check — never a second check pipeline (FR-001): - one page of /releases (ETag-conditional, so a repeat costs no rate-limit budget), plus a by-tag lookup only when the running build predates that page and its date is therefore unknown; - both requests share one context deadline. A per-request timeout bounds each hop and nothing bounds the total, and CheckNow runs synchronously inside GET /api/v1/info?refresh=true, so an unbounded delta would stall a request a user is waiting on; - counting is by semver, never by list position: GitHub orders the list by created_at, and the live data has v0.53.0-rc.9 sitting ahead of the later-published rc.10. Three degradation rules matter more than the feature. A delta miss must not set CheckError (statusVersionSuffix returns "" whenever it is non-empty, so that would DELETE the nudge instead of enriching it), must not touch the FR-018 backoff counters, and must leave every surface rendering exactly what it rendered before. There is a regression test per rule. The clause is rendered once in Go (FormatBehindSummary) and printed verbatim by every surface, with the raw numbers alongside for machine consumers. That is deliberate: GuidanceLine is already hand-ported into UpdateBanner.vue with a "keep the two in sync" comment, and FR-002 asks for consistent framing across five surfaces. Fields are additive per FR-021 and had to be threaded through six hand-maintained mirrors — VersionInfo, the InfoResponseUpdate DTO and its copier, internal/contracts (→ make swagger), the contracts.ts generator, status_cmd's map decoding, and the Swift tray's Codable, which turned out never to have decoded the US2 fields either. Two adjacent bugs fixed because the delta sits on the same code: - GetLatestReleaseIncludingPrereleases returned releases[0] from a created_at-ordered list, so an RC user could be offered a release older than one already published. Now max-by-semver. - GetReleaseByTag interpolated an unvalidated tag into the request path and deferred validation to callers by comment only. The delta feeds it the ldflags-stamped version, so it now validates and escapes. Both trays render the delta in the update item's tooltip rather than its title: Spec 092 FR-010 fixes the title's exact shape, and a menu row reading "Update v0.62.0 — ready to restart? — 8 releases / ~14 weeks behind" stops being scannable. Known bound, accepted deliberately: the scan reads one 100-release page, so a build older than that window reports a lower bound ("59+ releases") and a semver-in-range release created long ago can be missed without setting that flag. Spec 079's own assumption (L159) allows an approximation where an exact count is unavailable, and the figure is motivational, not load-bearing. Verified: unit + integration tests against an httptest GitHub (delta, saturation, tag fallback, 304 reuse, budget, malformed tags), `go test -race` across internal and cmd, golangci-lint v2 clean, 962 frontend unit tests, and a live version-stamped instance confirming the degradation path renders the pre-delta output when the check fails. * test(ux-audit): finish the sweep's regression net, and fix what it caught The August Web UI audit closes by asking for four assertions to be folded into the committed sweep. Three were already there (F9 contrast, F30 accessible names + aria-live, F14 responsive); this adds the two that were not, and then fixes the defects they immediately exposed on main. F6 — the Add Server modal takes focus, traps Tab, closes on Escape and restores focus to its trigger. These `<dialog :open>` modals are opened by the `open` attribute rather than showModal(), so none of that comes from the browser; it all comes from useModalA11y, whose own comment delegates the real-browser half of its coverage to "the Playwright sweep" — a promise the sweep did not keep. Escape is dispatched IN-PAGE, never via page.keyboard.press: re-checking F6 during the audit produced a false negative for exactly that reason, because a synthetic key never reaches the document listener under test. F1 — Activity and Usage must report the same 24h numbers as the API. The invariant is not naive equality: Usage folds `blocked` into its error tile while Activity splits them, and /activity/usage is served from a short read cache while /activity/summary counts live, so the assertion polls for convergence and encodes the real relationship. Running the completed sweep turned up three defects already on main, none of them regressions of the audit's 36: 1. The LANDING PAGE failed AA in both themes (3.09-4.23:1) and two of its controls had no accessible name. Usage.vue uses the raw `opacity-*` utility for muted text; #1054 fixed that failure mode for the text-base-content ramp and .stat-* but never covered raw opacity, and nothing caught it because the audit walked `/` before #1044 made Usage the landing page. Moved onto the AA-checked --tone-muted; both selects got an aria-label. 2. The Activity status pill clips at 390px for any status outside the known four. An unmapped status falls through to a ghost pill carrying the raw value, and `tool_auto_approved` measured 145px inside a 93px cell (the table is table-fixed below 640px). The pill now truncates against the cell and keeps the full value in its title, rather than the column being sized to today's longest label — which would hold only until the next status is added. The phone check that finally caught #2 had been passing vacuously: it measures rows.first(), and a `success` row — ~90% of traffic — renders an sr-only label of zero width. It only became a real assertion once the new F1 check generated an error row and put one first. That coupling is worth knowing about: the sweep shares one instance, so one check's traffic is the next check's data, and a newly-failing neighbour after adding a check is more likely a real find than a flake. Both were separated from the change under test by running the same sweep against clean HEAD. Sweep: 25 passed / 3 failed on clean HEAD, 30 passed / 0 failed now. Roadmap: ux-audit was still carrying both sweeps as `todo` although they and every finding shipped in August; recorded here along with what the completed net found.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes all 16 findings of the macOS tray UX + settings-parity audit (
docs/qa/ux-audit-macos-tray-2026-08.mdonaudit/ux-macos-tray-sweep), in the sequence that audit suggests.P1
Menu/TrayIcon.swift(a SwiftUI label nothing ever instantiated) is deleted along withAppState.healthLevel/HealthIndicator, andupdateStatusIcon()draws the red/orange severity dot itself. It is an attributed-title glyph, not a composite image: the status image must stayisTemplateto follow the menu bar, and a template image is re-rendered monochrome.updateStatusIcon()pass sets the image'saccessibilityDescription, the button'stoolTipand its accessibility label ("MCPProxy — 13/29 servers, 942 tools — 3 server errors").enable/disable/restart/loginno longer swallow errors. Oneperform(_:on:id:)helper dispatches all of them and raises an NSAlert on failure, offering Open Server Details / Report an Issue / Dismiss.Sign in,Restart) plus Open Server Details; rows with no action stay plain navigate-only rows.SidebarItem.tokenswires the finishedTokensViewinto the main window.P2
security.deep_scan.enabled,instructions(new.textareacontrol, placeholder fetched live from/api/v1/status.default_instructions) andcode_execution_max_paralleladded.scripts/check-settings-parity.py— already a required CI gate — was widened from duration fields to full key coverage plus control / placeholder / optional / step / min / max / restart / select options, excludingserver_edition.*. It strips comments, rejects duplicate keys and refuses a non-string-literal key rather than skipping it. It now pins 58 settings.Enable/Disableunconditionally; stdio no longer getsStart/Stop(which contradicted its own "Disabled" status line).Review quarantine…in the per-server submenu, deep-linking to Server Detail → Tools. Residual: (b) is not in this PR — a native Security section wrapping deep scans, scan reports and TPA findings is the audit's own L-sized item and wants its own spec.ActivityViewand seeds asession_idfilter with its own dismissable chip. Handed over onAppState, not by a delayed notification: a window created by the click subscribes its observers only after the post would have landed.P3
Protocol:is display-normalised (HTTP (streamable),HTTP (SSE),HTTP,stdio).512m/1.0/docker.ioplaceholders,steponentropy_thresholdandoauth_expiry_warning_hours(with a stepper control), telemetry copy caught up to the Web UI. All now held by the parity gate.ProjectLinks.issues/.discussionsare used: Report an Issue and Discussions in the About panel, in Settings → App, and as a button on the F3 failure alert. The unreferencedopenConfigFile()selector is deleted. Deviation from the audit's literal fix: not a new top-level menu row — fix(tray): slim the menu + represent code_execution by its sub-calls #1023 deliberately cut the menu to stop it scrolling andMenuStructureTestspins that; these homes cost no row.Disabled (N) ▸./api/v1/index/searchwhen it is not. (APIClient.searchToolswas calling/api/v1/tools?q=— an endpoint with noq— and reading a field that endpoint never returns, so it had always returned[]; nothing consumed it.)Three new Swift suites (
TrayPresentationTests,TrayAuditMenuTests,TrayAuditSurfacesTests) drive the realrebuildMenu()and the presentation rules; the suite is 1110 tests. No Go changes.Cross-model review
Reviewed with opencode (gpt-5.6-sol) over four rounds; every finding was verified against the source before being acted on, and round 4 returned CLEAN.
.urlQueryAllowed, which deliberately permits&,=,+and?— a tool search fora&limit=1became a second parameter. AddedAPIClient.escapeQueryValue; the activity list, the export and the tool search all use it.parent_id(pre-existing) or the newsession_id, so a filtered view exported the whole log. Both now come from the sameactiveFilterParamsthe list uses.worstDiagnosticSeveritylooks only at enabled servers; the label was counting every diagnostic of any severity. AddedAppState.diagnosticCount(severity:).:, somy/serverwould split the/servers/{id}/…path every menu action posts to. AddedAPIClient.escapePathComponent.optionalScalarStoredtrimmed spaces but not newlines — with the new textarea, a box holding one stray newline saved as custom instructions instead of resetting to the default.controlor a removed select option passed, and a non-literal key was skipped. All four now fail the gate (each verified by breaking the catalogue and watching it fail).