Repository navigation
fix(webui): honest server, connection and connect-modal states - #1053
Merged
Merged
Conversation
Web-UI UX audit (docs/qa/ux-audit-webui-2026-08.md) findings F7, F10, F11, F12, F17, F18, F28, F34 plus the F36 items in the same area. F7 — a quarantined server card stated "needs security review" and afforded no way to review. The card now carries a Review action deep-linked to the server's Security tab (where the spec-088 banner holds the verdict and the approve/scan actions), demotes Enable while the server is still held back, and the greyed Scan button says why it is disabled. F10 — the Dashboard "AI Agents" box read ClientStatus.connected from GET /api/v1/connect, which is content-read-free by design (Spec 075) and so reports connected=false for every client, always. The box could never say "Connected" while /sessions listed a live session on the same data. It now derives live clients from active MCP sessions — the same source /sessions and the macOS tray use — with a last-seen time and a link to the session. api.getSessions gains the backend's existing status filter so a small limit cannot be filled by closed sessions and hide a live client. F11 — a DNS failure offered "Restart", which redials the same broken address forever. health.Action now resolves to a new "edit_url" for address errors (no such host, unsupported/missing scheme, malformed URL); "connection refused" deliberately keeps Restart. The action deep-links to the Configuration tab with ?focus=endpoint, and the endpoint is editable there. The server detail page also spoke three status vocabularies at once (Enabled/Active, Online/Offline, Disconnected) with a green check on a server that was down; the tiles now carry exactly two axes — the admin state you set and the health level we observe — and the header badge uses the same unified reading as the Servers-page card. F12 — the Servers card printed the full wrapped Go error chain beside a perfectly good badge. The card shows the plain-language summary with the raw chain behind a details disclosure. The duplicated wrapper text is fixed at the source: mcp-go's streamable-HTTP transport wraps a send failure with the same message at two nesting levels, so adjacent duplicate segments are collapsed once, centrally, on last_error and on the diagnostic cause. F17 — the three registry cards sat above the selector looking exactly like one and were not clickable. They are the selector now (click or keyboard to toggle, visible selected state), the kebab menu no longer doubles as a selection, and the disabled search box says what would enable it. F18 — "connected" meant "the config holds an entry named mcpproxy", so a client pointing at a different instance on a different port showed as connected here. ClientStatus gains proxy_url, registered_url (sanitized the same way a preview's entry summary is) and endpoint_match (this/other/ unknown); a row addressing another instance says so and offers "Point here" instead of a false Disconnect. All rows use one action pattern, Disconnect confirms first and states the backup up front, Connect All names how many clients it would change and explains itself when it is off, and a client with no config names the paths that were searched. F28 — three surfaces for one cause: the auth modal, an inline load error behind it, and a "Connection Lost" toast. The modal now owns the message; the key field is labelled required rather than optional; "Continue Without Auth" is demoted and honest about leaving pages empty; and the key-recovery instructions no longer assume a tray, which headless and server installs do not have. F34 — the security tab printed the Risk Score twice and a bare coloured gauge with an unexplained number. One score, a labelled gauge, and a copyable scan id. F36 — the hub read "just started" on every page load because uptime was measured from when the page first saw the core running; /status and the SSE status frames now report the core's own started_at. The Sessions table's "View Activity" label no longer wraps onto two clipped lines.
Live verification of F12 turned up a defect in the fix itself: health.summary is only the mapped error phrase while a server is administratively enabled. For a disabled or quarantined server the calculator short-circuits and the summary describes the admin state, so the card's red alert read "Quarantined for review" — restating the quarantine banner directly below it instead of saying why the connection failed. Fall through to the structured diagnostic's user message, then to the raw chain's root cause. Also gives the server-detail Admin state tile a power symbol rather than the same gear the Tools tile uses: it is the on/off decision you made, not a configuration detail.
Deploying mcpproxy-docs with
|
| Latest commit: |
428b435
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://5f61f17f.mcpproxy-docs.pages.dev |
| Branch Preview URL: | https://fix-ux-servers-connect.mcpproxy-docs.pages.dev |
# Conflicts: # oas/docs.go
… inputs Cross-model review (opencode / gpt-5.6-sol) raised three findings on the backend seams. All three verified; all three addressed. 1. edit_url could be offered to a server with no URL to edit. The action was inferred from free-text last_error alone, and a stdio server emits exactly those phrases when its own network calls fail — an npx/uvx install that cannot reach its package registry says "no such host". HealthCalculatorInput gains HasEndpointURL, set from the configured URL, and ActionEditURL now requires it. Restart remains the remedy for stdio. 2. The wrapper collapse treated every ": " as a Go wrapping boundary, so an adjacent repeat inside a quoted URL, a JSON fragment, captured stderr or validation text would have been deleted silently. A segment is now dropped only when it also looks like wrapper prose: short, and made solely of letters, digits, spaces and word-joining marks. Anything carrying a quote, brace, bracket, slash or equals sign is payload and survives verbatim, even when it repeats. Tests cover each of those shapes. 3. registered_url was documented as "never a credential", which is stronger than the shared sanitizer guarantees: Spec 091's sanitizeEndpoint keeps scheme, host AND path, so a credential embedded in a path segment by a third-party config would survive — exactly as it already does on the connect preview surface. Reusing that sanitizer is deliberate, so the status row and the preview cannot disagree about what an entry says; the over-claim, not the behaviour, was the defect. Corrected in the Go comment, the TS type and the REST docs. Reviewer also confirmed no content-read regression in GetAllStatus (Spec 075 FR-001 intact), that the new real-endpoint-over-name-only matcher precedence removes a previously randomized choice rather than introducing one, that oauth.IsOAuthError still sees the pre-collapse error, and no nil-deref, unhandled error or concurrency defect.
…site Round-2 cross-model review found the HasEndpointURL gate was correct in runtime.GetAllServers but missing from the other two production projections (internal/server/server.go and internal/server/mcp.go). The field defaults to false and false is fail-safe, so nothing broke loudly — a URL-addressed server was simply offered "Restart" on the MCP `upstream_servers` list and the tray payload while the Web UI offered "Edit URL". Surfaces disagreeing about how to fix the same server is precisely the class of defect this change set exists to remove, and it is invisible to any single-surface test. Both call sites now set it from the configured URL, and a drift guard in the package that owns the contract asserts that any file calling CalculateHealth also mentions HasEndpointURL — verified to fail when the field is removed.
The drift guard matched the bare identifier, so a passing comment naming HasEndpointURL would have satisfied it — exactly the vacuous green the test exists to prevent. It now requires an actual assignment (a struct-literal field or a field write). Verified to fail when the assignment is replaced by a comment mentioning the field.
…view config internal/server/server.go already resolves the server's config fields through a storage fallback: when the stateview carries no Config it re-reads the stored upstream and fills `url` from that. My previous commit read serverStatus.Config.URL directly, so on exactly that fallback path an HTTP server would report HasEndpointURL=false and be offered Restart instead of Edit URL — reintroducing the surface disagreement one branch lower down. Use the resolved `url`. OAuthRequired is left reading serverStatus.Config exactly as before; changing its source is a separate question. internal/server/mcp.go needs no change: its `server` IS the config struct, with no fallback path.
Contributor
📦 Build ArtifactsWorkflow Run: View Run Available Artifacts
How to DownloadOption 1: GitHub Web UI (easiest)
Option 2: GitHub CLI gh run download 32877931041 --repo smart-mcp-proxy/mcpproxy-go
|
|
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
Dumbris
added a commit
that referenced
this pull request
Aug 26, 2026
The document read as an open P1–P3 backlog, but #1053 (merged 2026-08-25) fixed all 16 findings. Two readers in review took the header's "no version skew, so every finding below is reproducible from source" at face value against current main, where it is no longer true. - Header now scopes that claim to the time of the walk and carries a status banner pointing at #1053. - New §6 Resolution records the two fixes whose obvious implementation is wrong (F1's severity dot must be an attributed-title glyph, not a composite image, because the status image stays isTemplate; F6 added a parity gate, not just the three missing keys). - 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 #1053's diff, not from a second walk.
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
* 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.
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 — 5 server errors").enable/disable/restart/loginno longer swallow errors. Oneperform(_:on:id:)helper dispatches all of them and raises an NSAlert on failure, with 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 placeholder/optional/step/min/max, excludingserver_edition.*. 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. (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 needs its own spec.ActivityViewover a new.activityFilternotification and seeds asession_idfilter with its own dismissable chip.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.)Two new Swift suites (
TrayPresentationTests,TrayAuditMenuTests,TrayAuditSurfacesTests) drive the realrebuildMenu()and the presentation rules; the suite is 1107 tests. No Go changes.Cross-model review
Reviewed with opencode (gpt-5.6-sol), scoped to the Go seams. Every finding was verified against the source before being acted on.
Round 1 — three findings, all genuine, all fixed:
edit_urlcould be offered to a server with no URL. The action was inferred from free-textlast_erroralone, and a stdio server emits those phrases from its own failed network calls — an npx/uvx install that cannot reach its package registry saysno such host.HealthCalculatorInputgainedHasEndpointURL;ActionEditURLnow requires it. Verified live: a stdio server whoselast_errorcontainsno such hostreadsaction = restart, summary stillHost not found.": "as a wrapping boundary, so an adjacent repeat inside a quoted URL, JSON, captured stderr or validation text would have been deleted silently. A segment is now dropped only if it also looks like wrapper prose (short; letters, digits, spaces and word-joining marks only). Tests cover each payload shape the reviewer named.registered_urlwas documented as "never a credential", stronger than the shared sanitizer guarantees — Spec 091'ssanitizeEndpointkeeps scheme, host and path. Reusing it is deliberate (the status row and the connect preview must not disagree about what an entry says), so the over-claim was the defect. Corrected in the Go comment, the TS type and the REST docs.Reviewer also confirmed no content-read regression in
GetAllStatus(Spec 075 FR-001 intact), that the new real-endpoint-over-name-only matcher precedence removes a previously randomized choice rather than introducing one, thatoauth.IsOAuthErrorstill sees the pre-collapse error, and no nil-deref/unhandled-error/concurrency defect.Round 2 — one finding, genuine, fixed: the
HasEndpointURLgate was correct inruntime.GetAllServersbut missing from the other two production projections (internal/server/server.go,internal/server/mcp.go). The field defaults to false and false is fail-safe, so nothing broke loudly — the MCPupstream_serverslist and the tray payload simply offered Restart where the Web UI offered Edit URL. Surfaces disagreeing about how to fix the same server is the exact defect class this PR exists to remove, and it is invisible to any single-surface test. Both call sites now set it, and a drift guard in the package that owns the contract fails if a file callingCalculateHealthdoes not assign the field (verified to fail both when the assignment is deleted and when it is replaced by a comment naming it).