feat: add reasoning effort support for Codex models

- Add ReasoningEffortSelector component for UI selection
- Integrate reasoning effort in feature creation/editing dialogs
- Add reasoning effort support to phase model selector
- Update agent service and board actions to handle reasoning effort
- Add reasoning effort fields to feature and settings types
- Update model selector and agent info panel with reasoning effort display
- Enhance agent context parser for reasoning effort processing

Reasoning effort allows fine-tuned control over Codex model reasoning
capabilities, providing options from 'none' to 'xhigh' for different
task complexity requirements.

apps/ui/src/components/views/board-view/shared/index.ts

@@ -1,6 +1,7 @@
 export * from './model-constants';
 export * from './model-selector';
 export * from './thinking-level-selector';
+export * from './reasoning-effort-selector';
 export * from './profile-quick-select';
 export * from './profile-select';
 export * from './testing-tab-content';

apps/ui/src/components/views/board-view/shared/model-selector.tsx

@@ -45,8 +45,8 @@ export function ModelSelector({
       // Switch to Cursor's default model (from global settings)
       onModelSelect(`${PROVIDER_PREFIXES.cursor}${cursorDefaultModel}`);
     } else if (provider === 'codex' && selectedProvider !== 'codex') {
-      // Switch to Codex's default model (gpt-5.2)
-      onModelSelect('gpt-5.2');
+      // Switch to Codex's default model (gpt-5.2-codex)
+      onModelSelect('gpt-5.2-codex');
     } else if (provider === 'claude' && selectedProvider !== 'claude') {
       // Switch to Claude's default model
       onModelSelect('sonnet');

apps/ui/src/components/views/board-view/shared/reasoning-effort-selector.tsx

@@ -0,0 +1,47 @@
+import { Label } from '@/components/ui/label';
+import { Brain } from 'lucide-react';
+import { cn } from '@/lib/utils';
+import type { ReasoningEffort } from '@automaker/types';
+import { REASONING_EFFORT_LEVELS, REASONING_EFFORT_LABELS } from './model-constants';
+
+interface ReasoningEffortSelectorProps {
+  selectedEffort: ReasoningEffort;
+  onEffortSelect: (effort: ReasoningEffort) => void;
+  testIdPrefix?: string;
+}
+
+export function ReasoningEffortSelector({
+  selectedEffort,
+  onEffortSelect,
+  testIdPrefix = 'reasoning-effort',
+}: ReasoningEffortSelectorProps) {
+  return (
+    <div className="space-y-2 pt-2 border-t border-border">
+      <Label className="flex items-center gap-2 text-sm">
+        <Brain className="w-3.5 h-3.5 text-muted-foreground" />
+        Reasoning Effort
+      </Label>
+      <div className="flex gap-2 flex-wrap">
+        {REASONING_EFFORT_LEVELS.map((effort) => (
+          <button
+            key={effort}
+            type="button"
+            onClick={() => onEffortSelect(effort)}
+            className={cn(
+              'flex-1 px-3 py-2 rounded-md border text-sm font-medium transition-colors min-w-[60px]',
+              selectedEffort === effort
+                ? 'bg-primary text-primary-foreground border-primary'
+                : 'bg-background hover:bg-accent border-input'
+            )}
+            data-testid={`${testIdPrefix}-${effort}`}
+          >
+            {REASONING_EFFORT_LABELS[effort]}
+          </button>
+        ))}
+      </div>
+      <p className="text-xs text-muted-foreground">
+        Higher efforts give more reasoning tokens for complex problems.
+      </p>
+    </div>
+  );
+}