feat: enhance suggestion generation with model and thinking level overrides

- Updated the generateSuggestions function to accept model and thinking level overrides, allowing for more flexible suggestion generation.
- Modified the API client and UI components to support passing these new parameters, improving user control over the suggestion process.
- Introduced a new phase model for AI Suggestions in settings, enhancing the overall functionality and user experience.

apps/server/src/routes/suggestions/generate-suggestions.ts

@@ -1,14 +1,14 @@
 /**
  * Business logic for generating suggestions
  *
- * Model is configurable via phaseModels.enhancementModel in settings
- * (Feature Enhancement in the UI). Supports both Claude and Cursor models.
+ * Model is configurable via phaseModels.suggestionsModel in settings
+ * (AI Suggestions in the UI). Supports both Claude and Cursor models.
  */
 
 import { query } from '@anthropic-ai/claude-agent-sdk';
 import type { EventEmitter } from '../../lib/events.js';
 import { createLogger } from '@automaker/utils';
-import { DEFAULT_PHASE_MODELS, isCursorModel } from '@automaker/types';
+import { DEFAULT_PHASE_MODELS, isCursorModel, type ThinkingLevel } from '@automaker/types';
 import { resolvePhaseModel } from '@automaker/model-resolver';
 import { createSuggestionsOptions } from '../../lib/sdk-options.js';
 import { extractJsonWithArray } from '../../lib/json-extractor.js';
@@ -135,7 +135,9 @@ export async function generateSuggestions(
   suggestionType: string,
   events: EventEmitter,
   abortController: AbortController,
-  settingsService?: SettingsService
+  settingsService?: SettingsService,
+  modelOverride?: string,
+  thinkingLevelOverride?: ThinkingLevel
 ): Promise<void> {
   const typePrompts: Record<string, string> = {
     features: 'Analyze this project and suggest new features that would add value.',
@@ -171,11 +173,28 @@ The response will be automatically formatted as structured JSON.`;
     '[Suggestions]'
   );
 
-  // Get model from phase settings (Feature Enhancement = enhancementModel)
+  // Get model from phase settings (AI Suggestions = suggestionsModel)
+  // Use override if provided, otherwise fall back to settings
   const settings = await settingsService?.getGlobalSettings();
-  const phaseModelEntry =
-    settings?.phaseModels?.enhancementModel || DEFAULT_PHASE_MODELS.enhancementModel;
-  const { model, thinkingLevel } = resolvePhaseModel(phaseModelEntry);
+  let model: string;
+  let thinkingLevel: ThinkingLevel | undefined;
+
+  if (modelOverride) {
+    // Use explicit override - resolve the model string
+    const resolved = resolvePhaseModel({
+      model: modelOverride,
+      thinkingLevel: thinkingLevelOverride,
+    });
+    model = resolved.model;
+    thinkingLevel = resolved.thinkingLevel;
+  } else {
+    // Use settings-based model
+    const phaseModelEntry =
+      settings?.phaseModels?.suggestionsModel || DEFAULT_PHASE_MODELS.suggestionsModel;
+    const resolved = resolvePhaseModel(phaseModelEntry);
+    model = resolved.model;
+    thinkingLevel = resolved.thinkingLevel;
+  }
 
   logger.info('[Suggestions] Using model:', model);
 

apps/server/src/routes/suggestions/routes/generate.ts

@@ -5,6 +5,7 @@
 import type { Request, Response } from 'express';
 import type { EventEmitter } from '../../../lib/events.js';
 import { createLogger } from '@automaker/utils';
+import type { ThinkingLevel } from '@automaker/types';
 import { getSuggestionsStatus, setRunningState, getErrorMessage, logError } from '../common.js';
 import { generateSuggestions } from '../generate-suggestions.js';
 import type { SettingsService } from '../../../services/settings-service.js';
@@ -14,9 +15,16 @@ const logger = createLogger('Suggestions');
 export function createGenerateHandler(events: EventEmitter, settingsService?: SettingsService) {
   return async (req: Request, res: Response): Promise<void> => {
     try {
-      const { projectPath, suggestionType = 'features' } = req.body as {
+      const {
+        projectPath,
+        suggestionType = 'features',
+        model,
+        thinkingLevel,
+      } = req.body as {
         projectPath: string;
         suggestionType?: string;
+        model?: string;
+        thinkingLevel?: ThinkingLevel;
       };
 
       if (!projectPath) {
@@ -38,7 +46,15 @@ export function createGenerateHandler(events: EventEmitter, settingsService?: Se
       setRunningState(true, abortController);
 
       // Start generation in background
-      generateSuggestions(projectPath, suggestionType, events, abortController, settingsService)
+      generateSuggestions(
+        projectPath,
+        suggestionType,
+        events,
+        abortController,
+        settingsService,
+        model,
+        thinkingLevel
+      )
         .catch((error) => {
           logError(error, 'Generate suggestions failed (background)');
           events.emit('suggestions:event', {

apps/ui/src/components/views/board-view/dialogs/feature-suggestions-dialog.tsx

@@ -34,6 +34,8 @@ import {
 import { useAppStore, Feature } from '@/store/app-store';
 import { toast } from 'sonner';
 import { LogViewer } from '@/components/ui/log-viewer';
+import { useModelOverride } from '@/components/shared/use-model-override';
+import { ModelOverrideTrigger } from '@/components/shared/model-override-trigger';
 
 const logger = createLogger('FeatureSuggestions');
 
@@ -104,6 +106,11 @@ export function FeatureSuggestionsDialog({
 
   const { features, setFeatures } = useAppStore();
 
+  // Model override for suggestions
+  const { effectiveModelEntry, isOverridden, setOverride } = useModelOverride({
+    phase: 'suggestionsModel',
+  });
+
   // Initialize selectedIds when suggestions change
   useEffect(() => {
     if (suggestions.length > 0 && selectedIds.size === 0) {
@@ -173,7 +180,13 @@ export function FeatureSuggestionsDialog({
       setCurrentSuggestionType(suggestionType);
 
       try {
-        const result = await api.suggestions.generate(projectPath, suggestionType);
+        // Pass model and thinkingLevel from the effective model entry
+        const result = await api.suggestions.generate(
+          projectPath,
+          suggestionType,
+          effectiveModelEntry.model,
+          effectiveModelEntry.thinkingLevel
+        );
         if (!result.success) {
           toast.error(result.error || 'Failed to start generation');
           setIsGenerating(false);
@@ -184,7 +197,7 @@ export function FeatureSuggestionsDialog({
         setIsGenerating(false);
       }
     },
-    [projectPath, setIsGenerating, setSuggestions]
+    [projectPath, setIsGenerating, setSuggestions, effectiveModelEntry]
   );
 
   // Stop generating
@@ -330,6 +343,14 @@ export function FeatureSuggestionsDialog({
                 AI Suggestions
               </>
             )}
+            <ModelOverrideTrigger
+              currentModelEntry={effectiveModelEntry}
+              onModelChange={setOverride}
+              phase="suggestionsModel"
+              isOverridden={isOverridden}
+              size="sm"
+              variant="icon"
+            />
           </DialogTitle>
           <DialogDescription>
             {currentConfig

apps/ui/src/lib/electron.ts

@@ -14,6 +14,7 @@ import type {
   ModelAlias,
   GitHubComment,
   IssueCommentsResult,
+  ThinkingLevel,
 } from '@automaker/types';
 import { getJSON, setJSON, removeItem } from './storage';
 
@@ -282,7 +283,9 @@ export type SuggestionType = 'features' | 'refactoring' | 'security' | 'performa
 export interface SuggestionsAPI {
   generate: (
     projectPath: string,
-    suggestionType?: SuggestionType
+    suggestionType?: SuggestionType,
+    model?: string,
+    thinkingLevel?: ThinkingLevel
   ) => Promise<{ success: boolean; error?: string }>;
   stop: () => Promise<{ success: boolean; error?: string }>;
   status: () => Promise<{
@@ -2065,7 +2068,12 @@ let mockSuggestionsTimeout: NodeJS.Timeout | null = null;
 
 function createMockSuggestionsAPI(): SuggestionsAPI {
   return {
-    generate: async (projectPath: string, suggestionType: SuggestionType = 'features') => {
+    generate: async (
+      projectPath: string,
+      suggestionType: SuggestionType = 'features',
+      model?: string,
+      thinkingLevel?: ThinkingLevel
+    ) => {
       if (mockSuggestionsRunning) {
         return {
           success: false,
@@ -2074,7 +2082,11 @@ function createMockSuggestionsAPI(): SuggestionsAPI {
       }
 
       mockSuggestionsRunning = true;
-      logger.info(`Mock generating ${suggestionType} suggestions for: ${projectPath}`);
+      logger.info(
+        `Mock generating ${suggestionType} suggestions for: ${projectPath}` +
+          (model ? ` with model: ${model}` : '') +
+          (thinkingLevel ? ` thinkingLevel: ${thinkingLevel}` : '')
+      );
 
       // Simulate async suggestion generation
       simulateSuggestionsGeneration(suggestionType);

apps/ui/src/lib/http-api-client.ts

@@ -1305,8 +1305,13 @@ export class HttpApiClient implements ElectronAPI {
 
   // Suggestions API
   suggestions: SuggestionsAPI = {
-    generate: (projectPath: string, suggestionType?: SuggestionType) =>
-      this.post('/api/suggestions/generate', { projectPath, suggestionType }),
+    generate: (
+      projectPath: string,
+      suggestionType?: SuggestionType,
+      model?: string,
+      thinkingLevel?: string
+    ) =>
+      this.post('/api/suggestions/generate', { projectPath, suggestionType, model, thinkingLevel }),
     stop: () => this.post('/api/suggestions/stop'),
     status: () => this.get('/api/suggestions/status'),
     onEvent: (callback: (event: SuggestionsEvent) => void) => {