diff --git a/apps/server/src/providers/codex-provider.ts b/apps/server/src/providers/codex-provider.ts
index 18838cb8..5c200ea5 100644
--- a/apps/server/src/providers/codex-provider.ts
+++ b/apps/server/src/providers/codex-provider.ts
@@ -98,9 +98,14 @@ const TEXT_ENCODING = 'utf-8';
  * This is the "no output" timeout - if the CLI doesn't produce any JSONL output
  * for this duration, the process is killed. For reasoning models with high
  * reasoning effort, this timeout is dynamically extended via calculateReasoningTimeout().
+ *
+ * For feature generation (which can generate 50+ features), we use a much longer
+ * base timeout (5 minutes) since Codex models are slower at generating large JSON responses.
+ *
  * @see calculateReasoningTimeout from @automaker/types
  */
 const CODEX_CLI_TIMEOUT_MS = DEFAULT_TIMEOUT_MS;
+const CODEX_FEATURE_GENERATION_BASE_TIMEOUT_MS = 300000; // 5 minutes for feature generation
 const CONTEXT_WINDOW_256K = 256000;
 const MAX_OUTPUT_32K = 32000;
 const MAX_OUTPUT_16K = 16000;
@@ -827,7 +832,14 @@ export class CodexProvider extends BaseProvider {
       // Higher reasoning effort (e.g., 'xhigh' for "xtra thinking" mode) requires more time
       // for the model to generate reasoning tokens before producing output.
       // This fixes GitHub issue #530 where features would get stuck with reasoning models.
-      const timeout = calculateReasoningTimeout(options.reasoningEffort, CODEX_CLI_TIMEOUT_MS);
+      //
+      // For feature generation with 'xhigh', use the extended 5-minute base timeout
+      // since generating 50+ features takes significantly longer than normal operations.
+      const baseTimeout =
+        options.reasoningEffort === 'xhigh'
+          ? CODEX_FEATURE_GENERATION_BASE_TIMEOUT_MS
+          : CODEX_CLI_TIMEOUT_MS;
+      const timeout = calculateReasoningTimeout(options.reasoningEffort, baseTimeout);
 
       const stream = spawnJSONLProcess({
         command: commandPath,
diff --git a/apps/server/src/routes/app-spec/generate-features-from-spec.ts b/apps/server/src/routes/app-spec/generate-features-from-spec.ts
index 95e550e0..6558256b 100644
--- a/apps/server/src/routes/app-spec/generate-features-from-spec.ts
+++ b/apps/server/src/routes/app-spec/generate-features-from-spec.ts
@@ -8,7 +8,7 @@
 import * as secureFs from '../../lib/secure-fs.js';
 import type { EventEmitter } from '../../lib/events.js';
 import { createLogger } from '@automaker/utils';
-import { DEFAULT_PHASE_MODELS, supportsStructuredOutput } from '@automaker/types';
+import { DEFAULT_PHASE_MODELS, supportsStructuredOutput, isCodexModel } from '@automaker/types';
 import { resolvePhaseModel } from '@automaker/model-resolver';
 import { streamingQuery } from '../../providers/simple-query-service.js';
 import { parseAndCreateFeatures } from './parse-and-create-features.js';
@@ -26,6 +26,12 @@ const logger = createLogger('SpecRegeneration');
 
 const DEFAULT_MAX_FEATURES = 50;
 
+/**
+ * Timeout for Codex models when generating features (5 minutes).
+ * Codex models are slower and need more time to generate 50+ features.
+ */
+const CODEX_FEATURE_GENERATION_TIMEOUT_MS = 300000; // 5 minutes
+
 /**
  * Type for extracted features JSON response
  */
@@ -189,10 +195,23 @@ Generate ${featureCount} NEW features that build on each other logically. Rememb
         provider: undefined,
         credentials: undefined,
       };
-  const { model, thinkingLevel } = resolvePhaseModel(phaseModelEntry);
+  const { model, thinkingLevel, reasoningEffort } = resolvePhaseModel(phaseModelEntry);
 
   logger.info('Using model:', model, provider ? `via provider: ${provider.name}` : 'direct API');
 
+  // Codex models need extended timeout for generating many features.
+  // Use 'xhigh' reasoning effort to get 5-minute timeout (300s base * 1.0x = 300s).
+  // The Codex provider has a special 5-minute base timeout for feature generation.
+  const isCodex = isCodexModel(model);
+  const effectiveReasoningEffort = isCodex ? 'xhigh' : reasoningEffort;
+
+  if (isCodex) {
+    logger.info('Codex model detected - using extended timeout (5 minutes for feature generation)');
+  }
+  if (effectiveReasoningEffort) {
+    logger.info('Reasoning effort:', effectiveReasoningEffort);
+  }
+
   // Determine if we should use structured output based on model type
   const useStructuredOutput = supportsStructuredOutput(model);
   logger.info(
@@ -239,6 +258,7 @@ Your entire response should be valid JSON starting with { and ending with }. No
     allowedTools: ['Read', 'Glob', 'Grep'],
     abortController,
     thinkingLevel,
+    reasoningEffort: effectiveReasoningEffort, // Extended timeout for Codex models
     readOnly: true, // Feature generation only reads code, doesn't write
     settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
     claudeCompatibleProvider: provider, // Pass provider for alternative endpoint configuration
diff --git a/libs/model-resolver/src/resolver.ts b/libs/model-resolver/src/resolver.ts
index d642ecde..ebb36c44 100644
--- a/libs/model-resolver/src/resolver.ts
+++ b/libs/model-resolver/src/resolver.ts
@@ -32,6 +32,7 @@ import {
   migrateModelId,
   type PhaseModelEntry,
   type ThinkingLevel,
+  type ReasoningEffort,
 } from '@automaker/types';
 
 // Pattern definitions for Codex/OpenAI models
@@ -162,8 +163,10 @@ export function getEffectiveModel(
 export interface ResolvedPhaseModel {
   /** Resolved model string (full model ID) */
   model: string;
-  /** Optional thinking level for extended thinking */
+  /** Optional thinking level for extended thinking (Claude models) */
   thinkingLevel?: ThinkingLevel;
+  /** Optional reasoning effort for timeout calculation (Codex models) */
+  reasoningEffort?: ReasoningEffort;
   /** Provider ID if using a ClaudeCompatibleProvider */
   providerId?: string;
 }
@@ -205,6 +208,7 @@ export function resolvePhaseModel(
     return {
       model: resolveModelString(undefined, defaultModel),
       thinkingLevel: undefined,
+      reasoningEffort: undefined,
     };
   }
 
@@ -214,12 +218,13 @@ export function resolvePhaseModel(
     return {
       model: resolveModelString(phaseModel, defaultModel),
       thinkingLevel: undefined,
+      reasoningEffort: undefined,
     };
   }
 
   // Handle new PhaseModelEntry object format
   console.log(
-    `[ModelResolver] phaseModel is object format: model="${phaseModel.model}", thinkingLevel="${phaseModel.thinkingLevel}", providerId="${phaseModel.providerId}"`
+    `[ModelResolver] phaseModel is object format: model="${phaseModel.model}", thinkingLevel="${phaseModel.thinkingLevel}", reasoningEffort="${phaseModel.reasoningEffort}", providerId="${phaseModel.providerId}"`
   );
 
   // If providerId is set, pass through the model string unchanged
@@ -231,6 +236,7 @@ export function resolvePhaseModel(
     return {
       model: phaseModel.model, // Pass through unchanged
       thinkingLevel: phaseModel.thinkingLevel,
+      reasoningEffort: phaseModel.reasoningEffort,
       providerId: phaseModel.providerId,
     };
   }
@@ -239,5 +245,6 @@ export function resolvePhaseModel(
   return {
     model: resolveModelString(phaseModel.model, defaultModel),
     thinkingLevel: phaseModel.thinkingLevel,
+    reasoningEffort: phaseModel.reasoningEffort,
   };
 }