Consolidate search-first shell UX

docs-archived/implplan/SPRINT_20260307_036_FE_search_first_shell_consolidation.md

@@ -19,7 +19,7 @@
 ## Delivery Tracker
 
 ### FE-SF-001 - Consolidate shell language around search-first entry
-Status: TODO
+Status: DONE
 Dependency: none
 Owners: Developer
 Task description:
@@ -27,12 +27,12 @@ Task description:
 - Keep the compact assistant icon beside the search field, but use secondary "details/deeper help" language in the primary surface.
 
 Completion criteria:
-- [ ] The top-bar search surface reads as one workflow with a secondary assistant action.
+- [x] The top-bar search surface reads as one workflow with a secondary assistant action.
-- [ ] Answer-panel and launcher labels no longer imply a competing primary entry model.
+- [x] Answer-panel and launcher labels no longer imply a competing primary entry model.
-- [ ] No search-origin assistant action performs a route jump.
+- [x] No search-origin assistant action performs a route jump.
 
 ### FE-SF-002 - Make automatic result shaping clearer than mechanics
-Status: TODO
+Status: DONE
 Dependency: FE-SF-001
 Owners: Developer
 Task description:
@@ -40,12 +40,12 @@ Task description:
 - Keep `Did you mean` directly below the input and avoid any scope or refinement teaching copy.
 
 Completion criteria:
-- [ ] `Did you mean` stays input-adjacent.
+- [x] `Did you mean` stays input-adjacent.
-- [ ] Overflow is visibly secondary and uses plain operator-facing labels.
+- [x] Overflow is visibly secondary and uses plain operator-facing labels.
-- [ ] No recovery/refinement mechanics are rendered in the primary flow.
+- [x] No recovery/refinement mechanics are rendered in the primary flow.
 
 ### FE-SF-003 - Tighten suggestion handling and successful history behavior
-Status: TODO
+Status: DONE
 Dependency: FE-SF-002
 Owners: Developer
 Task description:
@@ -53,12 +53,12 @@ Task description:
 - Keep history success-only and make the clear-history affordance remain low-emphasis.
 
 Completion criteria:
-- [ ] Starter chips disappear when backend viability marks them non-executable.
+- [x] Starter chips disappear when backend viability marks them non-executable.
-- [ ] No-result searches never persist into history.
+- [x] No-result searches never persist into history.
-- [ ] The clear-history action remains a discreet icon treatment.
+- [x] The clear-history action remains a discreet icon treatment.
 
 ### FE-SF-004 - Verify the shell consolidation paths
-Status: TODO
+Status: DONE
 Dependency: FE-SF-003
 Owners: Developer, Test Automation
 Task description:
@@ -66,18 +66,20 @@ Task description:
 - Cover suggestion execution and no-result history behavior in the FE surface.
 
 Completion criteria:
-- [ ] Angular tests cover updated labels, answer/overflow presentation, and success-only history behavior.
+- [x] Angular tests cover updated labels, answer/overflow presentation, and success-only history behavior.
-- [ ] Playwright covers search-first entry, assistant launch from search, and suggestion execution on the simplified shell.
+- [x] Playwright covers search-first entry, assistant launch from search, and suggestion execution on the simplified shell.
-- [ ] No visible mode or scope controls appear in covered flows.
+- [x] No visible mode or scope controls appear in covered flows.
 
 ## Execution Log
 | Date (UTC) | Update | Owner |
 | --- | --- | --- |
 | 2026-03-07 | Sprint created for the FE shell consolidation half of the final search-first correction pass. | Project Manager |
+| 2026-03-07 | Reduced primary-surface assistant branding to secondary "deeper help/details" language, relabeled the drawer to `Search assistant`, tightened overflow wording, and added self-correcting starter suppression for suggestion chips that execute to no useful result. Verification: `npm test -- --include src/tests/global_search/global-search.component.spec.ts --include src/tests/advisory_ai_chat/chat.component.spec.ts --include src/tests/advisory_ai_chat/chat-message.component.spec.ts` -> `34/34` passed; `npx playwright test tests/e2e/unified-search-experience-quality.e2e.spec.ts tests/e2e/unified-search-self-serve-answer-panel.e2e.spec.ts tests/e2e/unified-search-contextual-suggestions.e2e.spec.ts --config playwright.config.ts` -> `16/16` passed. | Developer / Test Automation |
 
 ## Decisions & Risks
 - Decision: assistant remains available but secondary; search is the first-class workflow.
 - Decision: current-scope weighting is communicated through answer ordering, not control surfaces.
+- Decision: starter chips that fail at execution time are immediately suppressed from the current page context instead of being shown again as if they were trustworthy.
 - Risk: shell-level copy and layout may still imply a separate assistant product even after earlier cleanup.
 - Mitigation: change the primary-surface labels and add focused FE regression coverage.
 - Reference: `docs/modules/ui/search-zero-learning-primary-entry.md`

docs/modules/ui/TASKS.md

@@ -9,8 +9,6 @@
 - `docs/implplan/SPRINT_20260307_009_DOCS_ui_component_preservation_map.md`
 - `docs/implplan/SPRINT_20260307_022_FE_policy_vex_release_decisioning_studio.md`
 - `docs/implplan/SPRINT_20260307_023_DOCS_ui_restoration_topic_shapes.md`
-- `docs/implplan/SPRINT_20260307_035_DOCS_search_first_final_correction_phases.md`
-- `docs/implplan/SPRINT_20260307_036_FE_search_first_shell_consolidation.md`
 - `docs/implplan/SPRINT_20260307_038_FE_live_search_supported_route_execution_matrix.md`
 
 ## Delivery Tasks
@@ -50,10 +48,10 @@
 - [DONE] FE-UX-E2E Playwright coverage for mode switching, rescue flows, and AdvisoryAI next-step cards
 - [DONE] WEB-CTX-NONOBVIOUS Strategic non-obvious suggestion recipes (cross-domain + action-aware)
 - [DOING] FE-QA-LOOP-001 Web-only Playwright full-iteration loop at stella-ops.local (fresh route/action evidence, triage, fix, retest)
-- [TODO] FE-SF-001 Search-first shell language consolidation
+- [DONE] FE-SF-001 Search-first shell language consolidation
-- [TODO] FE-SF-002 Automatic answer/overflow presentation cleanup
+- [DONE] FE-SF-002 Automatic answer/overflow presentation cleanup
-- [TODO] FE-SF-003 Suggestion execution and success-only history hardening
+- [DONE] FE-SF-003 Suggestion execution and success-only history hardening
-- [TODO] FE-SF-004 Search-first shell verification coverage
+- [DONE] FE-SF-004 Search-first shell verification coverage
 - [TODO] QA-SF-001 Live route preflight and corpus readiness gate
 - [TODO] QA-SF-002 Execute surfaced suggestions on supported routes
 - [TODO] QA-SF-003 Align deterministic and live search-first matrices

docs/modules/ui/search-zero-learning-primary-entry.md

@@ -122,6 +122,7 @@
 - Implemented before the corrective phases: the live Doctor suggestion suite now rebuilds the active corpus, fails on empty knowledge projections, iterates every surfaced suggestion, and verifies Ask-AdvisoryAI inherits the live search context.
 - Implemented from the corrective phases: backend overflow is now narrow enough that clear in-scope winners suppress out-of-scope spillover, blended summaries only appear for genuinely close evidence clusters, and `SearchTelemetryEnabled` cleanly disables analytics/feedback/sink emission without affecting retrieval or history.
 - Implemented from the operator-correction pass: FE search contracts no longer depend on hidden `Find / Explain / Act` metadata, starter chips wait for backend viability before rendering, `Did you mean` is the first in-panel cue under the search field, and successful recent history now uses a structured `stella-successful-searches-v3` contract that ignores legacy bare-string entries on load.
+- Implemented from the final correction pass: the primary surface now uses secondary "deeper help/details" assistant language instead of presenting a separate AdvisoryAI product, overflow results read as supporting context, and starter chips that execute to no useful result are suppressed from the current page until context changes.
 - Still pending from the corrective phases: stricter backend viability states across more domains, broader live-page matrices, and explicit client-side telemetry opt-out.
 
 ## Execution phases - operator correction pass

src/Web/StellaOps.Web/src/app/features/advisory-ai/chat/chat-message.component.ts

@@ -79,7 +79,7 @@ interface NextStepCard {
       <!-- Message content -->
       <div class="message-content">
         <header class="message-header">
-          <span class="message-role">{{ turn.role === 'user' ? 'You' : 'AdvisoryAI' }}</span>
+          <span class="message-role">{{ turn.role === 'user' ? 'You' : 'Assistant' }}</span>
           <time class="message-time" [attr.datetime]="turn.timestamp">
             {{ formatTime(turn.timestamp) }}
           </time>

src/Web/StellaOps.Web/src/app/features/advisory-ai/chat/chat.component.ts

@@ -55,7 +55,7 @@ import {
               <path d="M16 15.5v.01"/>
               <path d="M12 12v.01"/>
             </svg>
-            <h2 class="header-title">AdvisoryAI</h2>
+            <h2 class="header-title">Search assistant</h2>
             @if (conversation()) {
               <span class="conversation-id">{{ conversation()!.conversationId.substring(0, 8) }}</span>
             }
@@ -110,7 +110,7 @@ import {
               <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
                 <path d="M21 15a2 2 0 0 1-2 2H7l-4 4V5a2 2 0 0 1 2-2h14a2 2 0 0 1 2 2z"/>
               </svg>
-              <h3>Ask AdvisoryAI</h3>
+              <h3>Go deeper</h3>
               <p>{{ emptyStateDescription() }}</p>
               <div class="suggestions">
                 @for (suggestion of suggestions(); track suggestion) {
@@ -144,7 +144,7 @@ import {
                 </div>
                 <div class="message-content">
                   <header class="message-header">
-                    <span class="message-role">AdvisoryAI</span>
+                    <span class="message-role">Assistant</span>
                     <span class="typing-indicator">
                       @if (progressStage()) {
                         {{ progressStage() }}

src/Web/StellaOps.Web/src/app/layout/global-search/global-search.component.ts

@@ -49,6 +49,7 @@ type SearchStarterView = {
   query: string;
   kind: 'question' | 'suggestion';
 };
+type SuggestedExecutionSource = 'starter' | 'question' | 'answer-next' | 'did-you-mean';
 type SearchContextPanelView = {
   title: string;
   description: string;
@@ -106,8 +107,8 @@ type SuccessfulSearchHistoryEntry = {
         <button
           type="button"
           class="search__chat-launcher"
-          [attr.aria-label]="t('ui.search.chat_launcher', 'Open AdvisoryAI chat')"
+          [attr.aria-label]="t('ui.search.chat_launcher', 'Open deeper help')"
-          [title]="t('ui.search.chat_launcher', 'Open AdvisoryAI chat')"
+          [title]="t('ui.search.chat_launcher', 'Open deeper help')"
           (mousedown)="$event.preventDefault()"
           (click)="openAssistantFromSearchBar()"
         >
@@ -162,7 +163,7 @@ type SuccessfulSearchHistoryEntry = {
                   data-answer-action="ask-ai"
                   (click)="openAssistantForAnswerPanel()"
                 >
-                  {{ t('ui.search.answer.ask_ai', 'Ask AdvisoryAI') }}
+                  {{ t('ui.search.answer.ask_ai', 'Open details') }}
                 </button>
               </div>
               <div class="search__answer-evidence">{{ answer.evidence }}</div>
@@ -328,7 +329,7 @@ type SuccessfulSearchHistoryEntry = {
 
             @if (starterQueries().length > 0) {
               <div class="search__suggestions">
-                <div class="search__group-label">{{ t('ui.search.starters.label', 'Try asking') }}</div>
+                <div class="search__group-label">{{ t('ui.search.starters.label', 'Start here') }}</div>
                 <div class="search__starter-chips">
                   @for (starter of starterQueries(); track starter.query) {
                     <button
@@ -927,6 +928,9 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   private readonly recentSearchStorageKey = 'stella-successful-searches-v3';
   private readonly legacySuccessfulSearchStorageKey = 'stella-successful-searches-v2';
   private readonly legacyRecentSearchStorageKey = 'stella-recent-searches';
+  private pendingSuggestedExecution:
+    | { query: string; source: SuggestedExecutionSource }
+    | null = null;
   private wasDegradedMode = false;
   private escapeCount = 0;
   private placeholderRotationHandle: ReturnType<typeof setInterval> | null = null;
@@ -947,6 +951,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   readonly searchResponse = signal<UnifiedSearchResponse | null>(null);
   readonly suggestionViability = signal<SearchSuggestionViabilityResponse | null>(null);
   readonly recentSearches = signal<string[]>([]);
+  readonly suppressedStarterQueries = signal<string[]>([]);
   readonly expandedCardKey = signal<string | null>(null);
 
   readonly showResults = computed(() =>
@@ -1092,7 +1097,10 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   readonly contextualSuggestions = computed<SearchSuggestionView[]>(() => {
     return [...this.ambientContext.getSearchSuggestions()]
       .sort((left, right) => this.scoreSuggestion(right) - this.scoreSuggestion(left))
-      .filter((suggestion) => this.isSuggestionQueryViable(this.i18n.tryT(suggestion.key) ?? suggestion.fallback))
+      .filter((suggestion) => {
+        const query = this.i18n.tryT(suggestion.key) ?? suggestion.fallback;
+        return this.isSuggestionQueryViable(query) && !this.isStarterQuerySuppressed(query);
+      })
       .map((suggestion) => ({
         query: this.i18n.tryT(suggestion.key) ?? suggestion.fallback,
         reason: this.resolveSuggestionReason(suggestion),
@@ -1103,7 +1111,10 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   readonly commonQuestions = computed<SearchQuestionView[]>(() => {
     return [...this.ambientContext.getCommonQuestions()]
       .sort((left, right) => this.scoreQuestion(right) - this.scoreQuestion(left))
-      .filter((question) => this.isSuggestionQueryViable(this.i18n.tryT(question.key) ?? question.fallback))
+      .filter((question) => {
+        const query = this.i18n.tryT(question.key) ?? question.fallback;
+        return this.isSuggestionQueryViable(query) && !this.isStarterQuerySuppressed(query);
+      })
       .map((question) => ({
         query: this.i18n.tryT(question.key) ?? question.fallback,
         kind: question.kind ?? 'page',
@@ -1165,7 +1176,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
       return {
         status: 'grounded',
         eyebrow,
-        title: this.t('ui.search.answer.title.find', 'What we found'),
+        title: this.t('ui.search.answer.title.find', 'Best answer'),
         summary: this.buildGroundedAnswerSummary(response),
         evidence: this.buildGroundedEvidenceLabel(response),
         citations: this.buildAnswerCitations(response),
@@ -1269,7 +1280,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
       }));
   });
   readonly overflowSectionTitle = computed(() =>
-    this.t('ui.search.results.overflow', 'Also worth checking'));
+    this.t('ui.search.results.overflow', 'Also relevant elsewhere'));
   readonly overflowSectionReason = computed(() =>
     this.searchResponse()?.overflow?.reason
       ?? this.t(
@@ -1295,6 +1306,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
       )
       .subscribe(() => {
         this.consumeChatToSearchContext();
+        this.clearSuppressedStarterQueries();
         if (this.isFocused()) {
           this.refreshSuggestionViability();
         }
@@ -1355,6 +1367,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
             Math.max(1, response.cards.length + overflowCount),
           );
         }
+        this.reconcileSuggestedExecution(response);
 
         // Sprint 106 / G6: Emit search analytics events
         this.emitSearchAnalytics(response);
@@ -1415,6 +1428,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
     this.query.set(value);
     this.selectedIndex.set(0);
     this.escapeCount = 0;
+    this.pendingSuggestedExecution = null;
     if (value.trim().length === 0) {
       this.refreshSuggestionViability();
     }
@@ -1594,6 +1608,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   }
 
   applyExampleQuery(example: string): void {
+    this.trackSuggestedExecution(example, 'starter');
     this.recordAmbientAction('search_example', {
       source: 'global_search_example_chip',
       queryHint: example,
@@ -1604,6 +1619,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   }
 
   applyQuestionQuery(query: string, source: 'common' | 'answer' | 'clarify'): void {
+    this.trackSuggestedExecution(query, source === 'common' ? 'starter' : 'question');
     const action = source === 'common'
       ? 'search_common_question'
       : source === 'clarify'
@@ -1619,6 +1635,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   }
 
   applyAnswerNextSearch(query: string): void {
+    this.trackSuggestedExecution(query, 'answer-next');
     this.recordAmbientAction('search_answer_next_search', {
       source: 'global_search_self_serve',
       queryHint: query,
@@ -1629,6 +1646,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
   }
 
   applySuggestion(text: string): void {
+    this.trackSuggestedExecution(text, 'did-you-mean');
     this.recordAmbientAction('search_suggestion', {
       source: 'global_search_did_you_mean',
       queryHint: text,
@@ -1952,7 +1970,7 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
       case 'insufficient':
         return this.t('ui.search.answer.title.insufficient', 'Not enough evidence yet');
       default:
-        return this.t('ui.search.answer.title.find', 'What we found');
+        return this.t('ui.search.answer.title.find', 'Best answer');
     }
   }
 
@@ -1993,6 +2011,11 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
     return match ? match.viable : false;
   }
 
+  private isStarterQuerySuppressed(query: string): boolean {
+    const normalized = this.normalizeQueryKey(query);
+    return normalized.length > 0 && this.suppressedStarterQueries().includes(normalized);
+  }
+
   private refreshSuggestionViability(): void {
     if (!this.isFocused()) {
       return;
@@ -2091,6 +2114,19 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
     });
   }
 
+  private trackSuggestedExecution(query: string, source: SuggestedExecutionSource): void {
+    const normalized = query.trim();
+    if (!normalized) {
+      this.pendingSuggestedExecution = null;
+      return;
+    }
+
+    this.pendingSuggestedExecution = {
+      query: normalized,
+      source,
+    };
+  }
+
   private resolveSuggestionReason(suggestion: {
     reasonKey?: string;
     reasonFallback?: string;
@@ -2195,6 +2231,23 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
       || (response.synthesis?.sourceCount ?? 0) > 0;
   }
 
+  private reconcileSuggestedExecution(response: UnifiedSearchResponse): void {
+    const pending = this.pendingSuggestedExecution;
+    if (!pending) {
+      return;
+    }
+
+    if (this.normalizeQueryKey(response.query) !== this.normalizeQueryKey(pending.query)) {
+      return;
+    }
+
+    if (!this.hasSearchEvidence(response)) {
+      this.suppressStarterQuery(response.query);
+    }
+
+    this.pendingSuggestedExecution = null;
+  }
+
   private persistRecentSearches(entries: readonly SuccessfulSearchHistoryEntry[]): void {
     this.recentSearches.set(entries.map((entry) => entry.query));
     try {
@@ -2220,6 +2273,28 @@ export class GlobalSearchComponent implements OnInit, OnDestroy {
       .slice(0, 10);
   }
 
+  private suppressStarterQuery(query: string): void {
+    const normalized = this.normalizeQueryKey(query);
+    if (!normalized) {
+      return;
+    }
+
+    this.suppressedStarterQueries.update((queries) =>
+      queries.includes(normalized)
+        ? queries
+        : [...queries, normalized],
+    );
+  }
+
+  private clearSuppressedStarterQueries(): void {
+    this.pendingSuggestedExecution = null;
+    this.suppressedStarterQueries.set([]);
+  }
+
+  private normalizeQueryKey(query: string): string {
+    return query.trim().toLowerCase();
+  }
+
   private normalizeActionRoute(route: string): string {
     return normalizeSearchActionRoute(route);
   }

src/Web/StellaOps.Web/src/app/layout/search-assistant-host/search-assistant-host.component.ts

@@ -28,7 +28,7 @@ import { ChatComponent } from '../../features/advisory-ai/chat';
           class="assistant-host__drawer assistant-drawer"
           role="dialog"
           aria-modal="true"
-          aria-label="AdvisoryAI assistant"
+          aria-label="Search assistant"
           tabindex="-1"
         >
           <stellaops-chat

src/Web/StellaOps.Web/src/tests/advisory_ai_chat/chat-message.component.spec.ts

@@ -46,7 +46,7 @@ describe('ChatMessageComponent (advisory_ai_chat)', () => {
   it('renders assistant role and grounding score', () => {
     const text = fixture.nativeElement.textContent as string;
 
-    expect(text).toContain('AdvisoryAI');
+    expect(text).toContain('Assistant');
     expect(text).toContain('88%');
   });
 

src/Web/StellaOps.Web/src/tests/advisory_ai_chat/chat.component.spec.ts

@@ -97,7 +97,11 @@ describe('ChatComponent (advisory_ai_chat)', () => {
     const suggestionButtons = fixture.nativeElement.querySelectorAll('.suggestion-btn');
     const textarea = fixture.nativeElement.querySelector('.chat-input') as HTMLTextAreaElement | null;
     const emptyState = fixture.nativeElement.querySelector('.empty-state p') as HTMLElement | null;
+    const heading = fixture.nativeElement.querySelector('.header-title') as HTMLElement | null;
+    const emptyHeading = fixture.nativeElement.querySelector('.empty-state h3') as HTMLElement | null;
 
+    expect(heading?.textContent).toContain('Search assistant');
+    expect(emptyHeading?.textContent).toContain('Go deeper');
     expect(emptyState?.textContent).toContain('current page');
     expect(suggestionButtons[0].textContent.trim()).toBe(
       'Summarize what matters here and what I should do next.',

src/Web/StellaOps.Web/src/tests/global_search/global-search.component.spec.ts

@@ -504,7 +504,7 @@ describe('GlobalSearchComponent', () => {
 
     const answerPanel = fixture.nativeElement.querySelector('[data-answer-status="grounded"]') as HTMLElement | null;
     expect(answerPanel).not.toBeNull();
-    expect(answerPanel?.textContent).toContain('What we found');
+    expect(answerPanel?.textContent).toContain('Best answer');
     expect(answerPanel?.textContent).toContain('Current-scope findings matched first, with one related policy hit held as overflow.');
     expect(answerPanel?.textContent).toContain('Grounded in 2 sources across Findings and Policy.');
     expect(answerPanel?.textContent).toContain('findings sample');
@@ -554,10 +554,61 @@ describe('GlobalSearchComponent', () => {
     const overflowSection = fixture.nativeElement.querySelector('[data-overflow-results]') as HTMLElement | null;
     expect(overflowSection).not.toBeNull();
     expect(fixture.nativeElement.querySelector('.search__scope-hint')).toBeNull();
-    expect(overflowSection?.textContent).toContain('Also worth checking');
+    expect(overflowSection?.textContent).toContain('Also relevant elsewhere');
     expect(overflowSection?.textContent).toContain('Related policy evidence is relevant but secondary to the Doctor page context.');
   });
 
+  it('suppresses a starter query after it executes with no results', async () => {
+    searchClient.search.and.returnValues(
+      of({
+        query: 'How do I deploy?',
+        topK: 10,
+        cards: [],
+        synthesis: null,
+        diagnostics: {
+          ftsMatches: 0,
+          vectorMatches: 0,
+          entityCardCount: 0,
+          durationMs: 2,
+          usedVector: false,
+          mode: 'fts-only',
+        },
+      }),
+      of({
+        query: '',
+        topK: 10,
+        cards: [],
+        synthesis: null,
+        diagnostics: {
+          ftsMatches: 0,
+          vectorMatches: 0,
+          entityCardCount: 0,
+          durationMs: 0,
+          usedVector: false,
+          mode: 'fts-only',
+        },
+      }),
+    );
+
+    component.onFocus();
+    fixture.detectChanges();
+    component.applyStarterQuery({ query: 'How do I deploy?', kind: 'suggestion' });
+    await waitForDebounce();
+    fixture.detectChanges();
+
+    expect(component.recentSearches()).toEqual([]);
+    expect(component.suppressedStarterQueries()).toContain('how do i deploy?');
+
+    component.onQueryChange('');
+    fixture.detectChanges();
+
+    const starterButtons = Array.from(
+      fixture.nativeElement.querySelectorAll('[data-starter-kind]') as NodeListOf<HTMLButtonElement>,
+    ).map((node) => node.textContent?.trim());
+
+    expect(starterButtons).not.toContain('How do I deploy?');
+  });
+
   it('suppresses contextual chips marked non-viable by backend suggestion evaluation', () => {
     searchClient.evaluateSuggestions.and.returnValue(of({
       suggestions: [

src/Web/StellaOps.Web/tests/e2e/unified-search-experience-quality.e2e.spec.ts

@@ -154,6 +154,7 @@ test.describe('Unified Search - Experience Quality UX', () => {
     await page.locator('.search__chat-launcher').click();
 
     await expect(page.locator('.assistant-drawer')).toBeVisible({ timeout: 10_000 });
+    await expect(page.locator('.header-title')).toContainText('Search assistant');
     await expect(page.locator('app-global-search input[type="text"]')).toHaveValue('');
     await expect.poll(() => capturedTurnBodies.length).toBeGreaterThan(0);
 
@@ -192,6 +193,54 @@ test.describe('Unified Search - Experience Quality UX', () => {
     await waitForEntityCards(page, 1);
   });
 
+  test('suppresses a starter chip after it executes to no results and keeps it out of history', async ({ page }) => {
+    await page.route('**/search/query**', async (route) => {
+      const request = route.request().postDataJSON() as Record<string, unknown>;
+      const query = String(request['q'] ?? '').toLowerCase();
+      const response = query.includes('critical findings')
+        ? emptyResponse('critical findings')
+        : criticalFindingResponse;
+
+      return route.fulfill({
+        status: 200,
+        contentType: 'application/json',
+        body: JSON.stringify(response),
+      });
+    });
+
+    await page.route('**/api/v1/advisory-ai/search/history', async (route) => {
+      if (route.request().method() === 'DELETE') {
+        return route.fulfill({ status: 204, body: '' });
+      }
+
+      return route.fulfill({
+        status: 200,
+        contentType: 'application/json',
+        body: JSON.stringify({ entries: [] }),
+      });
+    });
+
+    await page.goto('/security/triage');
+    await expect(page.locator('aside.sidebar')).toBeVisible({ timeout: 15_000 });
+
+    const searchInput = page.locator('app-global-search input[type="text"]');
+    await searchInput.focus();
+    await waitForResults(page);
+
+    const failingChip = page.locator('[data-starter-kind]', { hasText: /critical findings/i }).first();
+    await expect(failingChip).toBeVisible();
+
+    await failingChip.click();
+    await waitForResults(page);
+    await expect(page.locator('.search__empty')).toContainText('No results found');
+
+    await searchInput.fill('');
+    await waitForResults(page);
+
+    await expect(page.locator('[data-starter-kind]', { hasText: /critical findings/i })).toHaveCount(0);
+    await expect(page.locator('.search__group').filter({ hasText: 'Recent' })).toHaveCount(0);
+  });
+
   test('renders did-you-mean directly below the search bar and removes teaching controls', async ({ page }) => {
     const capturedRequests: Array<Record<string, unknown>> = [];
     await page.route('**/search/query**', async (route) => {
@@ -310,7 +359,7 @@ test.describe('Unified Search - Experience Quality UX', () => {
       /current-page findings matched first/i,
     );
     await expect(page.locator('.search__scope-hint')).toHaveCount(0);
-    await expect(page.locator('[data-overflow-results]')).toContainText(/also worth checking/i);
+    await expect(page.locator('[data-overflow-results]')).toContainText(/also relevant elsewhere/i);
     await expect(page.locator('[data-overflow-results]')).toContainText(/policy results remain relevant/i);
     await expect(page.locator('[data-role="domain-filter"]')).toHaveCount(0);
     await expect(page.locator('app-synthesis-panel')).toHaveCount(0);

src/Web/StellaOps.Web/tests/e2e/unified-search-self-serve-answer-panel.e2e.spec.ts

@@ -97,7 +97,7 @@ test.describe('Unified Search - Self-Serve Answer Panel', () => {
 
     const answerPanel = page.locator('[data-answer-status="grounded"]');
     await expect(answerPanel).toBeVisible();
-    await expect(answerPanel).toContainText('What we found');
+    await expect(answerPanel).toContainText('Best answer');
     await expect(answerPanel).toContainText('A reachable critical finding is blocking the current workflow and policy review is warranted.');
     await expect(answerPanel).toContainText('Grounded in 2 source(s) across Findings, Policy.');
     await expect(answerPanel.locator('[data-answer-citation]')).toContainText(['CVE-2024-21626 in api-gateway']);
@@ -156,6 +156,7 @@ test.describe('Unified Search - Self-Serve Answer Panel', () => {
     await page.locator('[data-answer-action="ask-ai"]').click();
 
     await expect(page.locator('.assistant-drawer')).toBeVisible({ timeout: 10_000 });
+    await expect(page.locator('.header-title')).toContainText('Search assistant');
     await expect(page.locator('.chat-message.user .message-body').first()).toContainText(/Expand the grounded answer/i);
     await expect(page.locator('.chat-message.user .message-body').first()).toContainText(/critical findings/i);
     await expect.poll(() => capturedTurnBodies.length).toBeGreaterThan(0);