Merge remote-tracking branch 'origin/master' into feat/read-image-context

# Conflicts:
#	docs/config-catalog.i18n.yaml
#	docs/config-catalog.md
#	docs/config-catalog.zh.md
#	packages/support/llm-replay/src/index.ts
#	packages/support/llm-replay/tests/llm-replay.spec.ts

packages/support/llm-replay/src/index.ts

@@ -25,7 +25,7 @@ import type {
   StreamChunk,
   TokenUsage,
 } from '@deepseek-ai/dsh-llm'
-import { LlmAdapter, LlmError, assertNever, resolveRetryPolicy } from '@deepseek-ai/dsh-llm'
+import { LlmAdapter, LlmError, ReasoningEffortId, assertNever, resolveRetryPolicy } from '@deepseek-ai/dsh-llm'
 
 /**
  * One recorded model call. `throw` may replay prefix chunks before failing;
@@ -54,6 +54,18 @@ export interface ReplayModelConfig {
   contextWindow?: number
   /** Optional declared input modalities, so a scenario can exercise capability gates (e.g. image-capable `read_image`). */
   inputModalities?: readonly ModelModality[]
+  /**
+   * 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
 }
 
 /** One provider route exposed by the replay adapter. */
@@ -592,6 +604,19 @@ class ReplayAdapter extends LlmAdapter {
       ...configuredModel?.contextWindow === undefined
         ? {}
         : { context: { contextWindow: configuredModel.contextWindow } },
+      ...configuredModel?.defaultMaxTokens === undefined
+        ? {}
+        : { defaultMaxTokens: configuredModel.defaultMaxTokens },
+      ...configuredModel?.reasoningEfforts === undefined
+        ? {}
+        : {
+          reasoning: {
+            efforts: configuredModel.reasoningEfforts.map(id => ({ id: ReasoningEffortId(id), name: id })),
+            ...configuredModel.defaultReasoningEffort === undefined
+              ? {}
+              : { defaultEffort: ReasoningEffortId(configuredModel.defaultReasoningEffort) },
+          },
+        },
     })
   }
 

packages/support/llm-replay/tests/llm-replay.spec.ts

@@ -593,8 +593,15 @@ describe('installLlmReplay (through the real LlmService)', () => {
             backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
           },
           models: [
-            { id: 'flash', contextWindow: 128_000, inputModalities: ['text', 'image'] },
-            { id: 'pro', name: 'Pro', description: 'Larger model' },
+            {
+              id: 'flash',
+              contextWindow: 128_000,
+              inputModalities: ['text', 'image'],
+              defaultMaxTokens: 64_000,
+              reasoningEfforts: ['off', 'max'],
+              defaultReasoningEffort: 'max',
+            },
+            { id: 'pro', name: 'Pro', description: 'Larger model', reasoningEfforts: ['high'] },
           ],
         },
         { id: 'empty' },
@@ -613,9 +620,19 @@ describe('installLlmReplay (through the real LlmService)', () => {
     await expect(ctx.llm.resolveModelInfo('deepseek', 'flash')).resolves.toMatchObject({
       context: { contextWindow: 128_000 },
       inputModalities: ['text', 'image'],
+      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('inputModalities')
     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({