diff --git a/docs/config-catalog.md b/docs/config-catalog.md
index b9ce45cd3c..d370fc945f 100644
--- a/docs/config-catalog.md
+++ b/docs/config-catalog.md
@@ -444,7 +444,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/fs/fs-local/src/index.ts:39`](../packages/fs/fs-local/src/index.ts)
+Source: [`packages/fs/fs-local/src/index.ts:40`](../packages/fs/fs-local/src/index.ts)
 
 ## `@deepseek-ai/dsh-fs-sandbox`
 
@@ -907,12 +907,24 @@ export interface ReplayModelConfig {
   description?: string
   /** Optional positive integer context capacity published by the replay adapter. */
   contextWindow?: number
+  /**
+   * Optional per-request output cap the replay route materializes when callers
+   * omit one, so replay reconstructs the request header a live catalog produced.
+   */
+  defaultMaxTokens?: number
+  /** Optional reasoning-effort ids the replay route accepts, in display order. */
+  reasoningEfforts?: string[]
+  /**
+   * Optional effort materialized when callers omit one; must appear in
+   * {@link reasoningEfforts} or call resolution rejects the route.
+   */
+  defaultReasoningEffort?: string
 }
 ```
 
 Depends on: [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts)
 
-Source: [`packages/support/llm-replay/src/index.ts:744`](../packages/support/llm-replay/src/index.ts)
+Source: [`packages/support/llm-replay/src/index.ts:769`](../packages/support/llm-replay/src/index.ts)
 
 ## `@deepseek-ai/dsh-llm-retry`
 
diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts
index 4be9e01c9d..8a30a23c5d 100644
--- a/packages/support/llm-replay/tests/llm-replay.spec.ts
+++ b/packages/support/llm-replay/tests/llm-replay.spec.ts
@@ -578,8 +578,14 @@ describe('installLlmReplay (through the real LlmService)', () => {
             backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
           },
           models: [
-            { id: 'flash', contextWindow: 128_000 },
-            { id: 'pro', name: 'Pro', description: 'Larger model' },
+            {
+              id: 'flash',
+              contextWindow: 128_000,
+              defaultMaxTokens: 64_000,
+              reasoningEfforts: ['off', 'max'],
+              defaultReasoningEffort: 'max',
+            },
+            { id: 'pro', name: 'Pro', description: 'Larger model', reasoningEfforts: ['high'] },
           ],
         },
         { id: 'empty' },
@@ -597,8 +603,18 @@ describe('installLlmReplay (through the real LlmService)', () => {
     await expect(ctx.llm.listModels('empty')).resolves.toEqual([])
     await expect(ctx.llm.resolveModelInfo('deepseek', 'flash')).resolves.toMatchObject({
       context: { contextWindow: 128_000 },
+      defaultMaxTokens: 64_000,
+      reasoning: {
+        efforts: [{ id: 'off', name: 'off' }, { id: 'max', name: 'max' }],
+        defaultEffort: 'max',
+      },
     })
     await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('context')
+    // Efforts without a configured default preserve the provider's own default.
+    await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.toMatchObject({
+      reasoning: { efforts: [{ id: 'high', name: 'high' }] },
+    })
+    await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('defaultMaxTokens')
     await expect(ctx.llm.resolveModelInfo('deepseek', 'unlisted')).resolves.not.toHaveProperty('context')
     await expect(ctx.llm.resolveModelInfo('empty', 'unlisted')).resolves.not.toHaveProperty('context')
     expect(ctx.llm.providerRetryPolicy('deepseek')).toMatchObject({