Repository navigation
docs(qa): Web UI UX audit — ranked findings (ux-audit epic) - #1046
Merged
Merged
Conversation
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).
Deploying mcpproxy-docs with
|
| Latest commit: |
91d8cf1
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://ae6bb3ee.mcpproxy-docs.pages.dev |
| Branch Preview URL: | https://audit-ux-webui-sweep.mcpproxy-docs.pages.dev |
|
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 32974796695 --repo smart-mcp-proxy/mcpproxy-go
|
github-actions Bot
pushed a commit
that referenced
this pull request
Aug 25, 2026
* fix(activity): count calls once, so Activity and Usage agree
The Activity Log header and the Dashboard's Usage tab reported different
totals for the same 24-hour window on the same instance. On a repro
instance the same traffic produced three numbers within seconds:
Activity header 51 calls (every activity record in the window)
Usage "Activity over time" 25 (calls the user made)
Usage "Tool calls" tile 19 (a client-side sum of `tools`)
The two Usage numbers sat on the same screen, one directly above the
other.
Root causes, one per surface:
* handleActivitySummary counted every record type as the header's
total, and the frontend labelled that total "N calls". Security
scans, quarantine auto-approvals and system starts are rows in the
log, not calls.
* Usage.vue summed `tools` client-side. That list is
lifetime-cumulative (the window only filters which tools appear),
upstream-only (mcpproxy's own retrieve_tools/describe_tool calls
vanish) and truncated to top-N (the tail is silently dropped).
Both now draw on one definition — storage.CountsAsCall — which the usage
aggregate already applied implicitly and now consults explicitly, so the
timeline, the summary endpoint, the Web UI and the CLI cannot drift
apart. The summary gains call_count/call_error_count; the usage response
gains total_calls/total_errors, computed server-side as the sum of the
timeline it carries. The event total is still reported, under its own
name, because it is the paginator's denominator.
After, on the same instance: Activity reads "83 events · 50 calls · 12
errors" and Usage reads "Calls 50 · Errors 12 · 24.0%".
Audit finding F1 (also F24) — #1046
* docs(storage): correct the call_tool_* exclusion rationale
ActivityFilter.ExcludeCallToolSuccess hides EVERY call_tool_* record, not
only successful ones — a dispatched call emits its own tool_call record
under the same request id whatever the outcome, and a shed one is written
by the limiter. So there is no pre-dispatch failure the counter loses;
the exclusion matches the list's own.
* docs(cli): show events and calls apart in the activity summary sample
* docs(contracts): disclose the usage read-cache skew on the parity contract
Cross-model review flagged that the usage endpoint serves a snapshot
behind observability.usage_cache_ttl (5s) while the summary endpoint
counts live, so a call can reach the Activity Log a few seconds before
the Usage tiles. That is inherent to the endpoint never scanning the log
per request (SC-005), it is bounded, and freshness_ms already discloses
it — so it is documented on the contract and in the parity test rather
than traded away.
* fix(httpapi): judge usage-cache freshness against the live TTL
usage_cache_ttl is hot-reloadable and it is the documented bound on how
far the Usage figures may lag the Activity Log. The cache banked an
absolute expiry from the TTL in force when the entry was written, so
lowering the TTL left entries alive past the new bound — an operator
tightening the bound got no effect until the old expiry passed. Entries
now record when they were stored and freshness is judged against the TTL
in force at read time.
Found by cross-model review of the F1 parity work.
* test(httpapi): age the usage-cache entry instead of trusting the clock
TestUsageCacheHonoursAHotReloadedTTL asserted a 1ns TTL rejects an entry
written moments earlier. On a Windows runner two adjacent time.Now()
calls can report zero elapsed time, so nothing was older than any TTL and
the test failed there. It now back-dates the entry by a minute and checks
a lowered TTL rejects it and a raised one accepts it — no sleeping, no
dependence on clock granularity.
Dumbris
added a commit
that referenced
this pull request
Aug 25, 2026
Audit findings F2, F5, F22, F23, F25, F26, F27 and the Activity/Usage part of F36 (#1046). Builds on #1048's storage.CountsAsCall contract. F2 — the status tiles are a partition again. ActivitySummaryResponse gains other_count: the rows whose status is outside the tool-call vocabulary (a quarantine change stores its action there, a policy decision its verdict). They were in the total and in no tile, so the row read 15+4+0+0 under a 42. The tile list now lives in one pure function, an "Other / internal" tile renders the residual, it filters like every other tile, and Go + Vitest tests assert the sum. F5 — repeats fold. Consecutive rows that agree on everything the collapsed line prints become one expandable run. Status is part of the run identity, so a run can never mix outcomes and "echo x12" can never hide the one call that failed; the sensitive-data flag and the code_execution parent link are in the identity for the same reason. Folding is on by default, remembered, and off whenever the table is sorted by something other than time. Successful rows no longer print "Success" at all — the word stays for screen readers only, so the marked rows in the column are exactly the ones needing a human. F22 — the usage charts stop inventing tools and stop quantizing latency. Names that never completed a call are excluded from "Calls per tool" and "Token sinks" (named in a footnote, still charted under errors, and counted the same way by the "active tools" tile). latencyBucketBoundsMs gains sub-10ms resolution, which is where local MCP servers live and where the old first bucket had none; Percentile now reports whether it hit the unbounded overflow bucket, so a figure renders as a bound ("<= 5 ms") or a floor ("> 10 s") and never as a stopwatch reading. Every chart axis says what it measures. F23 — the tokens-saved headline explains itself. It is a structural estimate over the current tool catalog, so it correctly does not move per call; the label said otherwise. Relabelled per-request, given the derivation on hover, and the Dashboard chip now opens the breakdown that computes it. F25 — a security_scan drawer shows its verdict and findings by severity and offers the server and the Security page. A session id is now a control: filter this log, or open Sessions. F26 — the Intent column paints the operation word beside the glyph, the Sensitive badge carries an accessible name, and the filter panel holds a visible legend for both. F27 — the Connected tile names its denominator ("2 of 3 enabled online"): a switched-off server is not an outage. serverCount.disabled is now asked directly and excludes quarantined servers, so the Dashboard rail stops reporting one server as two problems. F36 — the Sessions "View Activity" button stops clipping its label.
github-actions Bot
pushed a commit
that referenced
this pull request
Aug 25, 2026
…1052) * fix(webui): make the Activity and Usage numbers say what they mean Audit findings F2, F5, F22, F23, F25, F26, F27 and the Activity/Usage part of F36 (#1046). Builds on #1048's storage.CountsAsCall contract. F2 — the status tiles are a partition again. ActivitySummaryResponse gains other_count: the rows whose status is outside the tool-call vocabulary (a quarantine change stores its action there, a policy decision its verdict). They were in the total and in no tile, so the row read 15+4+0+0 under a 42. The tile list now lives in one pure function, an "Other / internal" tile renders the residual, it filters like every other tile, and Go + Vitest tests assert the sum. F5 — repeats fold. Consecutive rows that agree on everything the collapsed line prints become one expandable run. Status is part of the run identity, so a run can never mix outcomes and "echo x12" can never hide the one call that failed; the sensitive-data flag and the code_execution parent link are in the identity for the same reason. Folding is on by default, remembered, and off whenever the table is sorted by something other than time. Successful rows no longer print "Success" at all — the word stays for screen readers only, so the marked rows in the column are exactly the ones needing a human. F22 — the usage charts stop inventing tools and stop quantizing latency. Names that never completed a call are excluded from "Calls per tool" and "Token sinks" (named in a footnote, still charted under errors, and counted the same way by the "active tools" tile). latencyBucketBoundsMs gains sub-10ms resolution, which is where local MCP servers live and where the old first bucket had none; Percentile now reports whether it hit the unbounded overflow bucket, so a figure renders as a bound ("<= 5 ms") or a floor ("> 10 s") and never as a stopwatch reading. Every chart axis says what it measures. F23 — the tokens-saved headline explains itself. It is a structural estimate over the current tool catalog, so it correctly does not move per call; the label said otherwise. Relabelled per-request, given the derivation on hover, and the Dashboard chip now opens the breakdown that computes it. F25 — a security_scan drawer shows its verdict and findings by severity and offers the server and the Security page. A session id is now a control: filter this log, or open Sessions. F26 — the Intent column paints the operation word beside the glyph, the Sensitive badge carries an accessible name, and the filter panel holds a visible legend for both. F27 — the Connected tile names its denominator ("2 of 3 enabled online"): a switched-off server is not an outage. serverCount.disabled is now asked directly and excludes quarantined servers, so the Dashboard rail stops reporting one server as two problems. F36 — the Sessions "View Activity" button stops clipping its label. * fix(webui): widen the run identity to everything the folded row prints Cross-model review found three ways a run could fold away something the collapsed line was displaying on the members' behalf: - the intent OPERATION TYPE was not in the key, so a run of call_tool_write calls against a tool could fold under a "read" lead — the two produce records identical in type, server, tool and status. - only the sensitive-data BOOLEAN was in the key, but the badge prints the severity glyph and the detection count, so a critical detection could fold under a low-severity lead. - the key was a space-joined string over free-form fields (server name, tool name, details text), so two different rows could agree on one joined value. It is JSON.stringify now. The reason stays out of the key on purpose — that is what reasonsVary reports. Four regression tests, one per hazard. * fix(activity): stop dropping the scan findings summary, and clamp the page Three more from cross-model review. The settled-scan event carries its rollup as a map[string]int, and handleSecurityScanSettled read it with a map[string]interface{} type assertion that never matched — so findings_summary was dropped from every security_scan record ever written. Nothing noticed because nothing rendered it; F25's new drawer does. The read now takes the concrete type (and a JSON round-tripped one), and keeps an EMPTY rollup, because "the scanners found nothing" and "this record has no summary" are opposite claims and the drawer must not print the first when it only knows the second. It now says so, and points at the Security page. The Activity paginator never clamped currentPage, so folding repeats on while on a later page — or any refresh that shrinks the list — rendered an empty table with no hint why. Clamped on the derived page count, so every path is covered by one rule. Expanded runs and the page now also reset on a sort, session-filter or grouping change; a run key is a lead row's id, and a stale one re-expands the wrong run. The Usage "active tools" figure counts what is charted, so it now admits the folded tail when the server truncated the list. * fix(webui): three tie-breaks and one export that would come back empty Cross-model review, round three. Exporting from the "Other / internal" view sent that synthetic status to an endpoint that matches the closed vocabulary exactly, so the file came back empty — which reads as "there was nothing there". The export drops the status filter instead; a wider export is recoverable. Sorting by p95 could not tell a tool BOUNDED at the last histogram bucket from one that ran PAST it, and the response is truncated to top-N, so the genuinely slow tool could be dropped in favour of one that merely touched the ceiling. The overflow flag now breaks that tie. A failed scan can still carry findings: the debouncer keeps the last non-nil rollup, so a storm where some scanners finished and a later one failed settles as "failed" with real findings attached. The drawer shows them — hiding real findings is the worse error in a security view — and labels them as partial rather than as the scan's verdict.
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
force-pushed
the
audit/ux-webui-sweep
branch
from
August 26, 2026 13:32
a584333 to
91d8cf1
Compare
Dumbris
added a commit
that referenced
this pull request
Aug 27, 2026
…Web UI presentation defects (#1065) (#1072) * fix(quarantine): stop counting a quarantined server's tools as available (#1064) A quarantined server kept reporting its tools as available. `tool_count` stayed at its pre-quarantine value, `GET /api/v1/tools` returned every one of them, and the Servers page rendered the total under "Available across all servers" — while the search index correctly excluded them (#1061) and every call to those tools was refused with a SECURITY BLOCK. Two surfaces describing the same catalog disagreed, and the one an operator reads was the wrong one. Quarantine is neither "disabled" nor "disconnected": a quarantined server stays dialed with status ready on purpose, so the tray and Web UI can inspect it for review. It therefore passed the existing disabled/not-connected guard untouched. The stale count also survives the supervisor's disconnect-zeroing, because LoadConfiguredServers re-dials the server and the next reconcile re-sticks the retained snapshot. Adds one shared predicate, config.ServerContributesTools(enabled, quarantined), mirroring the answers runtime.serverEligibleForIndexing already gives the index writer and preflight.ClassifyTool gives dispatch, and adopts it at the surfaces that were each re-deriving "available" from a different field: - Projections zero the per-server count at the wire boundary: Runtime.GetAllServers, Server.GetAllServers, and both GetUpstreamStats paths (including the manager fallback, whose cached tool count no quarantine path invalidates). - Aggregates gate the sum: management.ListServers, Server.GetUpstreamStats, Manager.GetTotalToolCount. - GET /api/v1/tools and GET /api/v1/annotations/coverage skip quarantined servers. Skipping is a deliberate exclusion, not a fetch failure, so neither sets `partial`/`failed_servers`. - getVisibleToolCount returns 0 for a quarantined server. - The Web UI's totalTools excludes them too. Deliberately unchanged: - GET /api/v1/servers/{id}/tools still returns the full list. That is the review surface — it is how an operator inspects and approves a quarantined server, and after #1061 the StateView is its only source. Same for Server.GetQuarantinedServers, which exists to say how many tools await review. - isToolCallable stays quarantine-blind. It is the *search* filter and must reproduce merge-base semantics exactly (Spec 085 FR-006/FR-011), which require retrieve_tools to keep surfacing a quarantined server's lingering indexed tools; the stricter toolVisibleToSession applies the quarantine gate. TestVisibleToolCount_QuarantinedServer pins both halves so the two cannot be collapsed again. - stats.quarantined_servers and health admin_state=quarantined are untouched — they are the counterpart that must still show a non-zero number. Behaviour change worth calling out at review: users with quarantined servers will now report lower tool counts in /api/v1/status, the SSE servers.changed embed, /api/v1/profiles, the Prometheus tools-total gauge, the telemetry heartbeat, and the TOOLS column of `mcpproxy upstream list`. * fix(webui): three presentation defects — contradictory card, raw enum, stale auth error (#1065) 1. A server card asserted two contradictory security states at once The card rendered a green "Clean" scan verdict directly above a yellow "Quarantined — needs security review" banner. Both are individually true, but stacked as peers they tell the operator opposite things: the scan verdict is about CONTENT, quarantine is about REVIEW STATE. While quarantined, the standalone verdict badge is suppressed and the verdict is folded into the banner as a subordinate clause ("Last scan: clean — still needs review"), so the card carries exactly one security headline. This is the subordination ServerDetail's spec-088 banner already does, and the same shape as the #938 held-tools downgrade one level up. Nothing changes when the server is not quarantined. Every verdict still ends in a request to review, including the failed case, which is an INCOMPLETE scan and never a threat verdict. The Servers v-memo key gains security_scan.status and finding_counts.warning: the store updates server objects in place to preserve identity, so without them a scan settling on an already-quarantined server left a stale verdict. 2. The Activity Type column mixed two vocabularies formatType fell through `|| type` for anything unmapped, so raw snake_case landed in a column otherwise full of title-cased prose. Four backend types had no label, not the one reported: tool_quarantine_change, security_scan (already rendering raw today — it has had a findings drawer since #1046), credential_broker and prompt_get. The map is completed and exported as ACTIVITY_TYPE_LABELS, and the passthrough is replaced with a snake_case -> Title Case fallback so an unmapped value can never leak raw again. Server-level and tool-level quarantine keep distinct labels. The filter dropdown is derived from the same map instead of being hand-copied (it was three types short), and ActivityWidget's duplicate icon map is deleted in favour of the shared one. The recurrence guard lives in Go, not vitest: internal/storage/activity_label_parity_test.go fails when a backend type has no Web-UI label. .github/workflows/frontend.yml is path-filtered to frontend/**, so a vitest-only guard would never run on the Go-only change that adds a type. A second test asserts ValidActivityTypes covers every declared constant, so the first cannot go vacuously green. 3. A stale auth error survived a successful sign-in With no stored key, /ui/activity showed the auth modal, an inline red "Invalid or missing API key" panel behind it, and a Disconnected chip. Entering a valid key re-authenticated the header — counts and the Live badge came back — but the view body kept the red panel and rendered zero rows until the user clicked Retry by hand. Every view holds its load error in a component-local ref that nothing outside the component can reach, and no auth-recovered signal existed to reach it. Adds a monotonic authEpoch to the system store, bumped by markAuthRecovered() only on a genuine failed->ok transition. App.vue keys <router-view> on it, so a repaired auth remounts the current view and its error, loading state and data reset to their declared initial values while onMounted re-runs. Keyed on authEpoch alone: folding in the route path would remount ServerDetail on every :serverName change and break the Dashboard's single instance across /, /usage and /overview. reloadAfterAuth() re-primes the surfaces the key cannot reach (fetchInfo, fetchRouting, checkAuth — the router guard does not run for a key-driven remount), and SidebarNav watches the epoch for its badge counts rather than being remounted, which would also reset its open submenu and scroll. AuthErrorModal's "Refresh & Retry" now validates the reloaded key before reporting success and emits `refresh(verified)`. It previously cleared the auth flag without verifying anything, which is why it could not safely invalidate views — and why the stale panel survived on that path.
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.
Heuristic + live-instance UX audit of the Web UI for the
ux-auditepic (P0, gatesaction-log-transparency,analytics-default-landing,remote-access-tunnel).Every routed view walked in light and dark themes, first-run (empty config) and populated states, at 1440/820/390px, on two isolated cores (ports 18412/18413, scratch
--data-dirand--config). ~90 Playwright screenshots, programmatic WCAG contrast sampling, and real MCP traffic (reads/writes/destructive, failures, a sensitive-data hit, repeated identical calls). Screenshots are not committed — each finding names the state to reproduce.36 findings, ranked P0–P3, each with view, evidence, heuristic violated, suggested fix and S/M/L effort. Audited against Nielsen + empty/error/loading states + WCAG AA + responsive, plus the house activity-UI rules (grouping, failure-only status, intent reason, histogram/log parity).
Top of the backlog:
Usage.vuehas no route, no sidebar entry, no deep link.Docs-only.
websitebuild verified locally (npm ci && npm run build, exit 0, 168 documents processed).